diff options
Diffstat (limited to 'arch/x86/kernel')
59 files changed, 2239 insertions, 779 deletions
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index 0532f5d6e4e..b44577bc974 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -46,7 +46,7 @@ int acpi_suspend_lowlevel(void) header->pmode_behavior = 0; #ifndef CONFIG_64BIT - store_gdt((struct desc_ptr *)&header->pmode_gdt); + native_store_gdt((struct desc_ptr *)&header->pmode_gdt); if (!rdmsr_safe(MSR_EFER, &header->pmode_efer_low, diff --git a/arch/x86/kernel/acpi/wakeup_32.S b/arch/x86/kernel/acpi/wakeup_32.S index 13ab720573e..d1daa66ab16 100644 --- a/arch/x86/kernel/acpi/wakeup_32.S +++ b/arch/x86/kernel/acpi/wakeup_32.S @@ -1,4 +1,4 @@ - .section .text..page_aligned + .text #include <linux/linkage.h> #include <asm/segment.h> #include <asm/page_types.h> @@ -18,7 +18,6 @@ wakeup_pmode_return: movw %ax, %gs # reload the gdt, as we need the full 32 bit address - lgdt saved_gdt lidt saved_idt lldt saved_ldt ljmp $(__KERNEL_CS), $1f @@ -44,7 +43,6 @@ bogus_magic: save_registers: - sgdt saved_gdt sidt saved_idt sldt saved_ldt str saved_tss @@ -93,7 +91,6 @@ ENTRY(saved_magic) .long 0 ENTRY(saved_eip) .long 0 # saved registers -saved_gdt: .long 0,0 saved_idt: .long 0,0 saved_ldt: .long 0 saved_tss: .long 0 diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index ef5ccca79a6..c15cf9a25e2 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -271,7 +271,7 @@ void __init_or_module apply_alternatives(struct alt_instr *start, replacement = (u8 *)&a->repl_offset + a->repl_offset; BUG_ON(a->replacementlen > a->instrlen); BUG_ON(a->instrlen > sizeof(insnbuf)); - BUG_ON(a->cpuid >= NCAPINTS*32); + BUG_ON(a->cpuid >= (NCAPINTS + NBUGINTS) * 32); if (!boot_cpu_has(a->cpuid)) continue; diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index aadf3359e2a..3048ded1b59 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -20,12 +20,14 @@ const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_10H_NB_MISC) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_M10H_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3) }, {} }; EXPORT_SYMBOL(amd_nb_misc_ids); -static struct pci_device_id amd_nb_link_ids[] = { +static const struct pci_device_id amd_nb_link_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_15H_NB_F4) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F4) }, {} }; @@ -81,7 +83,6 @@ int amd_cache_northbridges(void) next_northbridge(link, amd_nb_link_ids); } - /* some CPU families (e.g. family 0x11) do not support GART */ if (boot_cpu_data.x86 == 0xf || boot_cpu_data.x86 == 0x10 || boot_cpu_data.x86 == 0x15) amd_northbridges.flags |= AMD_NB_GART; diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index d5fd66f0d4c..fd972a3e4cb 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -87,7 +87,7 @@ static u32 __init allocate_aperture(void) */ addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); - if (!addr || addr + aper_size > GART_MAX_ADDR) { + if (!addr) { printk(KERN_ERR "Cannot allocate aperture memory hole (%lx,%uK)\n", addr, aper_size>>10); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 66b5faffe14..53a4e274484 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -373,7 +373,6 @@ static int apm_cpu_idle(struct cpuidle_device *dev, static struct cpuidle_driver apm_idle_driver = { .name = "apm_idle", .owner = THIS_MODULE, - .en_core_tk_irqen = 1, .states = { { /* entry 0 is for polling */ }, { /* entry 1 is for APM idle */ diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c index 85d98ab15cd..0ef4bba2acb 100644 --- a/arch/x86/kernel/asm-offsets_32.c +++ b/arch/x86/kernel/asm-offsets_32.c @@ -60,6 +60,9 @@ void foo(void) OFFSET(IA32_RT_SIGFRAME_sigcontext, rt_sigframe, uc.uc_mcontext); BLANK(); + OFFSET(saved_context_gdt_desc, saved_context, gdt_desc); + BLANK(); + /* Offset from the sysenter stack to tss.sp0 */ DEFINE(TSS_sysenter_sp0, offsetof(struct tss_struct, x86_tss.sp0) - sizeof(struct tss_struct)); diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c index 1b4754f82ba..e7c798b354f 100644 --- a/arch/x86/kernel/asm-offsets_64.c +++ b/arch/x86/kernel/asm-offsets_64.c @@ -73,6 +73,7 @@ int main(void) ENTRY(cr3); ENTRY(cr4); ENTRY(cr8); + ENTRY(gdt_desc); BLANK(); #undef ENTRY diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile index a0e067d3d96..b0684e4a73a 100644 --- a/arch/x86/kernel/cpu/Makefile +++ b/arch/x86/kernel/cpu/Makefile @@ -14,7 +14,6 @@ CFLAGS_common.o := $(nostackp) obj-y := intel_cacheinfo.o scattered.o topology.o obj-y += proc.o capflags.o powerflags.o common.o -obj-y += vmware.o hypervisor.o mshyperv.o obj-y += rdrand.o obj-y += match.o @@ -31,7 +30,7 @@ obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o obj-$(CONFIG_PERF_EVENTS) += perf_event.o ifdef CONFIG_PERF_EVENTS -obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o +obj-$(CONFIG_CPU_SUP_AMD) += perf_event_amd.o perf_event_amd_uncore.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_p6.o perf_event_knc.o perf_event_p4.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_lbr.o perf_event_intel_ds.o perf_event_intel.o obj-$(CONFIG_CPU_SUP_INTEL) += perf_event_intel_uncore.o @@ -42,11 +41,13 @@ obj-$(CONFIG_MTRR) += mtrr/ obj-$(CONFIG_X86_LOCAL_APIC) += perfctr-watchdog.o perf_event_amd_ibs.o +obj-$(CONFIG_HYPERVISOR_GUEST) += vmware.o hypervisor.o mshyperv.o + quiet_cmd_mkcapflags = MKCAP $@ - cmd_mkcapflags = $(PERL) $(srctree)/$(src)/mkcapflags.pl $< $@ + cmd_mkcapflags = $(CONFIG_SHELL) $(srctree)/$(src)/mkcapflags.sh $< $@ cpufeature = $(src)/../../include/asm/cpufeature.h targets += capflags.c -$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.pl FORCE +$(obj)/capflags.c: $(cpufeature) $(src)/mkcapflags.sh FORCE $(call if_changed,mkcapflags) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index fa96eb0d02f..5013a48d1af 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -20,11 +20,11 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) { - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); u32 gprs[8] = { 0 }; int err; - WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + WARN_ONCE((boot_cpu_data.x86 != 0xf), + "%s should only be used on K8!\n", __func__); gprs[1] = msr; gprs[7] = 0x9c5a203a; @@ -38,10 +38,10 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p) static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val) { - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); u32 gprs[8] = { 0 }; - WARN_ONCE((c->x86 != 0xf), "%s should only be used on K8!\n", __func__); + WARN_ONCE((boot_cpu_data.x86 != 0xf), + "%s should only be used on K8!\n", __func__); gprs[0] = (u32)val; gprs[1] = msr; @@ -192,11 +192,11 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) /* Athlon 660/661 is valid. */ if ((c->x86_model == 6) && ((c->x86_mask == 0) || (c->x86_mask == 1))) - goto valid_k7; + return; /* Duron 670 is valid */ if ((c->x86_model == 7) && (c->x86_mask == 0)) - goto valid_k7; + return; /* * Athlon 662, Duron 671, and Athlon >model 7 have capability @@ -209,7 +209,7 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) ((c->x86_model == 7) && (c->x86_mask >= 1)) || (c->x86_model > 7)) if (cpu_has_mp) - goto valid_k7; + return; /* If we get here, not a certified SMP capable AMD system. */ @@ -220,9 +220,6 @@ static void __cpuinit amd_k7_smp_check(struct cpuinfo_x86 *c) WARN_ONCE(1, "WARNING: This combination of AMD" " processors is not suitable for SMP.\n"); add_taint(TAINT_UNSAFE_SMP, LOCKDEP_NOW_UNRELIABLE); - -valid_k7: - ; } static void __cpuinit init_amd_k7(struct cpuinfo_x86 *c) @@ -513,6 +510,10 @@ static void __cpuinit early_init_amd(struct cpuinfo_x86 *c) #endif } +static const int amd_erratum_383[]; +static const int amd_erratum_400[]; +static bool cpu_has_amd_erratum(const int *erratum); + static void __cpuinit init_amd(struct cpuinfo_x86 *c) { u32 dummy; @@ -727,8 +728,14 @@ static void __cpuinit init_amd(struct cpuinfo_x86 *c) rdmsrl_safe(MSR_AMD64_BU_CFG2, &value); value &= ~(1ULL << 24); wrmsrl_safe(MSR_AMD64_BU_CFG2, value); + + if (cpu_has_amd_erratum(amd_erratum_383)) + set_cpu_bug(c, X86_BUG_AMD_TLB_MMATCH); } + if (cpu_has_amd_erratum(amd_erratum_400)) + set_cpu_bug(c, X86_BUG_AMD_APIC_C1E); + rdmsr_safe(MSR_AMD64_PATCH_LEVEL, &c->microcode, &dummy); } @@ -847,8 +854,7 @@ cpu_dev_register(amd_cpu_dev); * AMD_OSVW_ERRATUM() macros. The latter is intended for newer errata that * have an OSVW id assigned, which it takes as first argument. Both take a * variable number of family-specific model-stepping ranges created by - * AMD_MODEL_RANGE(). Each erratum also has to be declared as extern const - * int[] in arch/x86/include/asm/processor.h. + * AMD_MODEL_RANGE(). * * Example: * @@ -858,16 +864,22 @@ cpu_dev_register(amd_cpu_dev); * AMD_MODEL_RANGE(0x10, 0x9, 0x0, 0x9, 0x0)); */ -const int amd_erratum_400[] = +#define AMD_LEGACY_ERRATUM(...) { -1, __VA_ARGS__, 0 } +#define AMD_OSVW_ERRATUM(osvw_id, ...) { osvw_id, __VA_ARGS__, 0 } +#define AMD_MODEL_RANGE(f, m_start, s_start, m_end, s_end) \ + ((f << 24) | (m_start << 16) | (s_start << 12) | (m_end << 4) | (s_end)) +#define AMD_MODEL_RANGE_FAMILY(range) (((range) >> 24) & 0xff) +#define AMD_MODEL_RANGE_START(range) (((range) >> 12) & 0xfff) +#define AMD_MODEL_RANGE_END(range) ((range) & 0xfff) + +static const int amd_erratum_400[] = AMD_OSVW_ERRATUM(1, AMD_MODEL_RANGE(0xf, 0x41, 0x2, 0xff, 0xf), AMD_MODEL_RANGE(0x10, 0x2, 0x1, 0xff, 0xf)); -EXPORT_SYMBOL_GPL(amd_erratum_400); -const int amd_erratum_383[] = +static const int amd_erratum_383[] = AMD_OSVW_ERRATUM(3, AMD_MODEL_RANGE(0x10, 0, 0, 0xff, 0xf)); -EXPORT_SYMBOL_GPL(amd_erratum_383); -bool cpu_has_amd_erratum(const int *erratum) +static bool cpu_has_amd_erratum(const int *erratum) { struct cpuinfo_x86 *cpu = __this_cpu_ptr(&cpu_info); int osvw_id = *erratum++; @@ -908,5 +920,3 @@ bool cpu_has_amd_erratum(const int *erratum) return false; } - -EXPORT_SYMBOL_GPL(cpu_has_amd_erratum); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index af6455e3fcc..4112be9a465 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -59,7 +59,7 @@ static void __init check_fpu(void) * trap_init() enabled FXSR and company _before_ testing for FP * problems here. * - * Test for the divl bug.. + * Test for the divl bug: http://en.wikipedia.org/wiki/Fdiv_bug */ __asm__("fninit\n\t" "fldl %1\n\t" @@ -75,26 +75,12 @@ static void __init check_fpu(void) kernel_fpu_end(); - boot_cpu_data.fdiv_bug = fdiv_bug; - if (boot_cpu_data.fdiv_bug) + if (fdiv_bug) { + set_cpu_bug(&boot_cpu_data, X86_BUG_FDIV); pr_warn("Hmm, FPU with FDIV bug\n"); + } } -/* - * Check whether we are able to run this kernel safely on SMP. - * - * - i386 is no longer supported. - * - In order to run on anything without a TSC, we need to be - * compiled for a i486. - */ - -static void __init check_config(void) -{ - if (boot_cpu_data.x86 < 4) - panic("Kernel requires i486+ for 'invlpg' and other features"); -} - - void __init check_bugs(void) { identify_boot_cpu(); @@ -102,7 +88,17 @@ void __init check_bugs(void) pr_info("CPU: "); print_cpu_info(&boot_cpu_data); #endif - check_config(); + + /* + * Check whether we are able to run this kernel safely on SMP. + * + * - i386 is no longer supported. + * - In order to run on anything without a TSC, we need to be + * compiled for a i486. + */ + if (boot_cpu_data.x86 < 4) + panic("Kernel requires i486+ for 'invlpg' and other features"); + init_utsname()->machine[1] = '0' + (boot_cpu_data.x86 > 6 ? 6 : boot_cpu_data.x86); alternative_instructions(); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index d814772c5be..22018f70a67 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -920,6 +920,10 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) /* AND the already accumulated flags with these */ for (i = 0; i < NCAPINTS; i++) boot_cpu_data.x86_capability[i] &= c->x86_capability[i]; + + /* OR, i.e. replicate the bug flags */ + for (i = NCAPINTS; i < NCAPINTS + NBUGINTS; i++) + c->x86_capability[i] |= boot_cpu_data.x86_capability[i]; } /* Init Machine Check Exception if available. */ diff --git a/arch/x86/kernel/cpu/cyrix.c b/arch/x86/kernel/cpu/cyrix.c index 4fbd384fb64..d048d5ca43c 100644 --- a/arch/x86/kernel/cpu/cyrix.c +++ b/arch/x86/kernel/cpu/cyrix.c @@ -249,7 +249,7 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* Emulate MTRRs using Cyrix's ARRs. */ set_cpu_cap(c, X86_FEATURE_CYRIX_ARR); /* 6x86's contain this bug */ - c->coma_bug = 1; + set_cpu_bug(c, X86_BUG_COMA); break; case 4: /* MediaGX/GXm or Geode GXM/GXLV/GX1 */ @@ -317,7 +317,8 @@ static void __cpuinit init_cyrix(struct cpuinfo_x86 *c) /* Enable MMX extensions (App note 108) */ setCx86_old(CX86_CCR7, getCx86_old(CX86_CCR7)|1); } else { - c->coma_bug = 1; /* 6x86MX, it has the bug. */ + /* A 6x86MX - it has the bug. */ + set_cpu_bug(c, X86_BUG_COMA); } tmp = (!(dir0_lsn & 7) || dir0_lsn & 1) ? 2 : 0; Cx86_cb[tmp] = cyrix_model_mult2[dir0_lsn & 7]; diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 1905ce98bee..9b0c441c03f 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -96,6 +96,18 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) sched_clock_stable = 1; } + /* Penwell and Cloverview have the TSC which doesn't sleep on S3 */ + if (c->x86 == 6) { + switch (c->x86_model) { + case 0x27: /* Penwell */ + case 0x35: /* Cloverview */ + set_cpu_cap(c, X86_FEATURE_NONSTOP_TSC_S3); + break; + default: + break; + } + } + /* * There is a known erratum on Pentium III and Core Solo * and Core Duo CPUs. @@ -164,20 +176,6 @@ int __cpuinit ppro_with_ram_bug(void) return 0; } -#ifdef CONFIG_X86_F00F_BUG -static void __cpuinit trap_init_f00f_bug(void) -{ - __set_fixmap(FIX_F00F_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); - - /* - * Update the IDT descriptor and reload the IDT so that - * it uses the read-only mapped virtual address. - */ - idt_descr.address = fix_to_virt(FIX_F00F_IDT); - load_idt(&idt_descr); -} -#endif - static void __cpuinit intel_smp_check(struct cpuinfo_x86 *c) { /* calling is from identify_secondary_cpu() ? */ @@ -206,16 +204,14 @@ static void __cpuinit intel_workarounds(struct cpuinfo_x86 *c) /* * All current models of Pentium and Pentium with MMX technology CPUs * have the F0 0F bug, which lets nonprivileged users lock up the - * system. - * Note that the workaround only should be initialized once... + * system. Announce that the fault handler will be checking for it. */ - c->f00f_bug = 0; + clear_cpu_bug(c, X86_BUG_F00F); if (!paravirt_enabled() && c->x86 == 5) { static int f00f_workaround_enabled; - c->f00f_bug = 1; + set_cpu_bug(c, X86_BUG_F00F); if (!f00f_workaround_enabled) { - trap_init_f00f_bug(); printk(KERN_NOTICE "Intel Pentium with F0 0F bug - workaround enabled.\n"); f00f_workaround_enabled = 1; } diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 7bc126346ac..9239504b41c 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -2358,7 +2358,7 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) if (action == CPU_POST_DEAD) { /* intentionally ignoring frozen here */ - cmci_rediscover(cpu); + cmci_rediscover(); } return NOTIFY_OK; diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c index 1ac581f38df..9cb52767999 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_amd.c +++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c @@ -33,7 +33,6 @@ #include <asm/mce.h> #include <asm/msr.h> -#define NR_BANKS 6 #define NR_BLOCKS 9 #define THRESHOLD_MAX 0xFFF #define INT_TYPE_APIC 0x00020000 @@ -57,12 +56,7 @@ static const char * const th_names[] = { "execution_unit", }; -static DEFINE_PER_CPU(struct threshold_bank * [NR_BANKS], threshold_banks); - -static unsigned char shared_bank[NR_BANKS] = { - 0, 0, 0, 0, 1 -}; - +static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks); static DEFINE_PER_CPU(unsigned char, bank_map); /* see which banks are on */ static void amd_threshold_interrupt(void); @@ -79,6 +73,12 @@ struct thresh_restart { u16 old_limit; }; +static inline bool is_shared_bank(int bank) +{ + /* Bank 4 is for northbridge reporting and is thus shared */ + return (bank == 4); +} + static const char * const bank4_names(struct threshold_block *b) { switch (b->address) { @@ -214,7 +214,7 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c) unsigned int bank, block; int offset = -1; - for (bank = 0; bank < NR_BANKS; ++bank) { + for (bank = 0; bank < mca_cfg.banks; ++bank) { for (block = 0; block < NR_BLOCKS; ++block) { if (block == 0) address = MSR_IA32_MC0_MISC + bank * 4; @@ -276,7 +276,7 @@ static void amd_threshold_interrupt(void) mce_setup(&m); /* assume first bank caused it */ - for (bank = 0; bank < NR_BANKS; ++bank) { + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, m.cpu) & (1 << bank))) continue; for (block = 0; block < NR_BLOCKS; ++block) { @@ -467,7 +467,7 @@ static __cpuinit int allocate_threshold_blocks(unsigned int cpu, u32 low, high; int err; - if ((bank >= NR_BANKS) || (block >= NR_BLOCKS)) + if ((bank >= mca_cfg.banks) || (block >= NR_BLOCKS)) return 0; if (rdmsr_safe_on_cpu(cpu, address, &low, &high)) @@ -575,7 +575,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) const char *name = th_names[bank]; int err = 0; - if (shared_bank[bank]) { + if (is_shared_bank(bank)) { nb = node_to_amd_nb(amd_get_nb_id(cpu)); /* threshold descriptor already initialized on this node? */ @@ -609,7 +609,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) per_cpu(threshold_banks, cpu)[bank] = b; - if (shared_bank[bank]) { + if (is_shared_bank(bank)) { atomic_set(&b->cpus, 1); /* nb is already initialized, see above */ @@ -635,9 +635,17 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank) static __cpuinit int threshold_create_device(unsigned int cpu) { unsigned int bank; + struct threshold_bank **bp; int err = 0; - for (bank = 0; bank < NR_BANKS; ++bank) { + bp = kzalloc(sizeof(struct threshold_bank *) * mca_cfg.banks, + GFP_KERNEL); + if (!bp) + return -ENOMEM; + + per_cpu(threshold_banks, cpu) = bp; + + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; err = threshold_create_bank(cpu, bank); @@ -691,7 +699,7 @@ static void threshold_remove_bank(unsigned int cpu, int bank) if (!b->blocks) goto free_out; - if (shared_bank[bank]) { + if (is_shared_bank(bank)) { if (!atomic_dec_and_test(&b->cpus)) { __threshold_remove_blocks(b); per_cpu(threshold_banks, cpu)[bank] = NULL; @@ -719,11 +727,12 @@ static void threshold_remove_device(unsigned int cpu) { unsigned int bank; - for (bank = 0; bank < NR_BANKS; ++bank) { + for (bank = 0; bank < mca_cfg.banks; ++bank) { if (!(per_cpu(bank_map, cpu) & (1 << bank))) continue; threshold_remove_bank(cpu, bank); } + kfree(per_cpu(threshold_banks, cpu)); } /* get notified when a cpu comes on/off */ diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c index 402c454fbff..ae1697c2afe 100644 --- a/arch/x86/kernel/cpu/mcheck/mce_intel.c +++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c @@ -285,39 +285,24 @@ void cmci_clear(void) raw_spin_unlock_irqrestore(&cmci_discover_lock, flags); } -static long cmci_rediscover_work_func(void *arg) +static void cmci_rediscover_work_func(void *arg) { int banks; /* Recheck banks in case CPUs don't all have the same */ if (cmci_supported(&banks)) cmci_discover(banks); - - return 0; } -/* - * After a CPU went down cycle through all the others and rediscover - * Must run in process context. - */ -void cmci_rediscover(int dying) +/* After a CPU went down cycle through all the others and rediscover */ +void cmci_rediscover(void) { - int cpu, banks; + int banks; if (!cmci_supported(&banks)) return; - for_each_online_cpu(cpu) { - if (cpu == dying) - continue; - - if (cpu == smp_processor_id()) { - cmci_rediscover_work_func(NULL); - continue; - } - - work_on_cpu(cpu, cmci_rediscover_work_func, NULL); - } + on_each_cpu(cmci_rediscover_work_func, NULL, 1); } /* diff --git a/arch/x86/kernel/cpu/mkcapflags.pl b/arch/x86/kernel/cpu/mkcapflags.pl deleted file mode 100644 index 091972ef49d..00000000000 --- a/arch/x86/kernel/cpu/mkcapflags.pl +++ /dev/null @@ -1,48 +0,0 @@ -#!/usr/bin/perl -w -# -# Generate the x86_cap_flags[] array from include/asm-x86/cpufeature.h -# - -($in, $out) = @ARGV; - -open(IN, "< $in\0") or die "$0: cannot open: $in: $!\n"; -open(OUT, "> $out\0") or die "$0: cannot create: $out: $!\n"; - -print OUT "#ifndef _ASM_X86_CPUFEATURE_H\n"; -print OUT "#include <asm/cpufeature.h>\n"; -print OUT "#endif\n"; -print OUT "\n"; -print OUT "const char * const x86_cap_flags[NCAPINTS*32] = {\n"; - -%features = (); -$err = 0; - -while (defined($line = <IN>)) { - if ($line =~ /^\s*\#\s*define\s+(X86_FEATURE_(\S+))\s+(.*)$/) { - $macro = $1; - $feature = "\L$2"; - $tail = $3; - if ($tail =~ /\/\*\s*\"([^"]*)\".*\*\//) { - $feature = "\L$1"; - } - - next if ($feature eq ''); - - if ($features{$feature}++) { - print STDERR "$in: duplicate feature name: $feature\n"; - $err++; - } - printf OUT "\t%-32s = \"%s\",\n", "[$macro]", $feature; - } -} -print OUT "};\n"; - -close(IN); -close(OUT); - -if ($err) { - unlink($out); - exit(1); -} - -exit(0); diff --git a/arch/x86/kernel/cpu/mkcapflags.sh b/arch/x86/kernel/cpu/mkcapflags.sh new file mode 100644 index 00000000000..2bf61650549 --- /dev/null +++ b/arch/x86/kernel/cpu/mkcapflags.sh @@ -0,0 +1,41 @@ +#!/bin/sh +# +# Generate the x86_cap_flags[] array from include/asm/cpufeature.h +# + +IN=$1 +OUT=$2 + +TABS="$(printf '\t\t\t\t\t')" +trap 'rm "$OUT"' EXIT + +( + echo "#ifndef _ASM_X86_CPUFEATURE_H" + echo "#include <asm/cpufeature.h>" + echo "#endif" + echo "" + echo "const char * const x86_cap_flags[NCAPINTS*32] = {" + + # Iterate through any input lines starting with #define X86_FEATURE_ + sed -n -e 's/\t/ /g' -e 's/^ *# *define *X86_FEATURE_//p' $IN | + while read i + do + # Name is everything up to the first whitespace + NAME="$(echo "$i" | sed 's/ .*//')" + + # If the /* comment */ starts with a quote string, grab that. + VALUE="$(echo "$i" | sed -n 's@.*/\* *\("[^"]*"\).*\*/@\1@p')" + [ -z "$VALUE" ] && VALUE="\"$NAME\"" + [ "$VALUE" == '""' ] && continue + + # Name is uppercase, VALUE is all lowercase + VALUE="$(echo "$VALUE" | tr A-Z a-z)" + + TABCOUNT=$(( ( 5*8 - 14 - $(echo "$NAME" | wc -c) ) / 8 )) + printf "\t[%s]%.*s = %s,\n" \ + "X86_FEATURE_$NAME" "$TABCOUNT" "$TABS" "$VALUE" + done + echo "};" +) > $OUT + +trap - EXIT diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c index a7d26d83fb7..8f4be53ea04 100644 --- a/arch/x86/kernel/cpu/mshyperv.c +++ b/arch/x86/kernel/cpu/mshyperv.c @@ -35,13 +35,6 @@ static bool __init ms_hyperv_platform(void) if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) return false; - /* - * Xen emulates Hyper-V to support enlightened Windows. - * Check to see first if we are on a Xen Hypervisor. - */ - if (xen_cpuid_base()) - return false; - cpuid(HYPERV_CPUID_VENDOR_AND_MAX_FUNCTIONS, &eax, &hyp_signature[0], &hyp_signature[1], &hyp_signature[2]); @@ -82,12 +75,6 @@ static void __init ms_hyperv_init_platform(void) if (ms_hyperv.features & HV_X64_MSR_TIME_REF_COUNT_AVAILABLE) clocksource_register_hz(&hyperv_cs, NSEC_PER_SEC/100); -#if IS_ENABLED(CONFIG_HYPERV) - /* - * Setup the IDT for hypervisor callback. - */ - alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); -#endif } const __refconst struct hypervisor_x86 x86_hyper_ms_hyperv = { @@ -103,6 +90,11 @@ static irq_handler_t vmbus_isr; void hv_register_vmbus_handler(int irq, irq_handler_t handler) { + /* + * Setup the IDT for hypervisor callback. + */ + alloc_intr_gate(HYPERVISOR_CALLBACK_VECTOR, hyperv_callback_vector); + vmbus_irq = irq; vmbus_isr = handler; } diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index bf0f01aea99..1025f3c99d2 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -180,8 +180,9 @@ static void release_pmc_hardware(void) {} static bool check_hw_exists(void) { - u64 val, val_new = ~0; - int i, reg, ret = 0; + u64 val, val_fail, val_new= ~0; + int i, reg, reg_fail, ret = 0; + int bios_fail = 0; /* * Check to see if the BIOS enabled any of the counters, if so @@ -192,8 +193,11 @@ static bool check_hw_exists(void) ret = rdmsrl_safe(reg, &val); if (ret) goto msr_fail; - if (val & ARCH_PERFMON_EVENTSEL_ENABLE) - goto bios_fail; + if (val & ARCH_PERFMON_EVENTSEL_ENABLE) { + bios_fail = 1; + val_fail = val; + reg_fail = reg; + } } if (x86_pmu.num_counters_fixed) { @@ -202,8 +206,11 @@ static bool check_hw_exists(void) if (ret) goto msr_fail; for (i = 0; i < x86_pmu.num_counters_fixed; i++) { - if (val & (0x03 << i*4)) - goto bios_fail; + if (val & (0x03 << i*4)) { + bios_fail = 1; + val_fail = val; + reg_fail = reg; + } } } @@ -221,14 +228,13 @@ static bool check_hw_exists(void) if (ret || val != val_new) goto msr_fail; - return true; - -bios_fail: /* * We still allow the PMU driver to operate: */ - printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); - printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg, val); + if (bios_fail) { + printk(KERN_CONT "Broken BIOS detected, complain to your hardware vendor.\n"); + printk(KERN_ERR FW_BUG "the BIOS has corrupted hw-PMU resources (MSR %x is %Lx)\n", reg_fail, val_fail); + } return true; @@ -1316,9 +1322,16 @@ static struct attribute_group x86_pmu_format_group = { */ static void __init filter_events(struct attribute **attrs) { + struct device_attribute *d; + struct perf_pmu_events_attr *pmu_attr; int i, j; for (i = 0; attrs[i]; i++) { + d = (struct device_attribute *)attrs[i]; + pmu_attr = container_of(d, struct perf_pmu_events_attr, attr); + /* str trumps id */ + if (pmu_attr->event_str) + continue; if (x86_pmu.event_map(i)) continue; @@ -1330,22 +1343,45 @@ static void __init filter_events(struct attribute **attrs) } } -static ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, +/* Merge two pointer arrays */ +static __init struct attribute **merge_attr(struct attribute **a, struct attribute **b) +{ + struct attribute **new; + int j, i; + + for (j = 0; a[j]; j++) + ; + for (i = 0; b[i]; i++) + j++; + j++; + + new = kmalloc(sizeof(struct attribute *) * j, GFP_KERNEL); + if (!new) + return NULL; + + j = 0; + for (i = 0; a[i]; i++) + new[j++] = a[i]; + for (i = 0; b[i]; i++) + new[j++] = b[i]; + new[j] = NULL; + + return new; +} + +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, char *page) { struct perf_pmu_events_attr *pmu_attr = \ container_of(attr, struct perf_pmu_events_attr, attr); - u64 config = x86_pmu.event_map(pmu_attr->id); - return x86_pmu.events_sysfs_show(page, config); -} -#define EVENT_VAR(_id) event_attr_##_id -#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + /* string trumps id */ + if (pmu_attr->event_str) + return sprintf(page, "%s", pmu_attr->event_str); -#define EVENT_ATTR(_name, _id) \ - PMU_EVENT_ATTR(_name, EVENT_VAR(_id), PERF_COUNT_HW_##_id, \ - events_sysfs_show) + return x86_pmu.events_sysfs_show(page, config); +} EVENT_ATTR(cpu-cycles, CPU_CYCLES ); EVENT_ATTR(instructions, INSTRUCTIONS ); @@ -1459,16 +1495,27 @@ static int __init init_hw_perf_events(void) unconstrained = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1, - 0, x86_pmu.num_counters, 0); + 0, x86_pmu.num_counters, 0, 0); x86_pmu.attr_rdpmc = 1; /* enable userspace RDPMC usage by default */ x86_pmu_format_group.attrs = x86_pmu.format_attrs; + if (x86_pmu.event_attrs) + x86_pmu_events_group.attrs = x86_pmu.event_attrs; + if (!x86_pmu.events_sysfs_show) x86_pmu_events_group.attrs = &empty_attrs; else filter_events(x86_pmu_events_group.attrs); + if (x86_pmu.cpu_events) { + struct attribute **tmp; + + tmp = merge_attr(x86_pmu_events_group.attrs, x86_pmu.cpu_events); + if (!WARN_ON(!tmp)) + x86_pmu_events_group.attrs = tmp; + } + pr_info("... version: %d\n", x86_pmu.version); pr_info("... bit width: %d\n", x86_pmu.cntval_bits); pr_info("... generic registers: %d\n", x86_pmu.num_counters); diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h index 7f5c75c2afd..ba9aadfa683 100644 --- a/arch/x86/kernel/cpu/perf_event.h +++ b/arch/x86/kernel/cpu/perf_event.h @@ -46,6 +46,7 @@ enum extra_reg_type { EXTRA_REG_RSP_0 = 0, /* offcore_response_0 */ EXTRA_REG_RSP_1 = 1, /* offcore_response_1 */ EXTRA_REG_LBR = 2, /* lbr_select */ + EXTRA_REG_LDLAT = 3, /* ld_lat_threshold */ EXTRA_REG_MAX /* number of entries needed */ }; @@ -59,7 +60,13 @@ struct event_constraint { u64 cmask; int weight; int overlap; + int flags; }; +/* + * struct event_constraint flags + */ +#define PERF_X86_EVENT_PEBS_LDLAT 0x1 /* ld+ldlat data address sampling */ +#define PERF_X86_EVENT_PEBS_ST 0x2 /* st data address sampling */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -170,16 +177,17 @@ struct cpu_hw_events { void *kfree_on_online; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o) {\ +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ { .idxmsk64 = (n) }, \ .code = (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ + .flags = f, \ } #define EVENT_CONSTRAINT(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0) + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) /* * The overlap flag marks event constraints with overlapping counter @@ -203,7 +211,7 @@ struct cpu_hw_events { * and its counter masks must be kept at a minimum. */ #define EVENT_CONSTRAINT_OVERLAP(c, n, m) \ - __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1) + __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 1, 0) /* * Constraint on the Event code. @@ -231,6 +239,14 @@ struct cpu_hw_events { #define INTEL_UEVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK) +#define INTEL_PLD_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT) + +#define INTEL_PST_CONSTRAINT(c, n) \ + __EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_ST) + #define EVENT_CONSTRAINT_END \ EVENT_CONSTRAINT(0, 0, 0) @@ -260,12 +276,22 @@ struct extra_reg { .msr = (ms), \ .config_mask = (m), \ .valid_mask = (vm), \ - .idx = EXTRA_REG_##i \ + .idx = EXTRA_REG_##i, \ } #define INTEL_EVENT_EXTRA_REG(event, msr, vm, idx) \ EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT, vm, idx) +#define INTEL_UEVENT_EXTRA_REG(event, msr, vm, idx) \ + EVENT_EXTRA_REG(event, msr, ARCH_PERFMON_EVENTSEL_EVENT | \ + ARCH_PERFMON_EVENTSEL_UMASK, vm, idx) + +#define INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(c) \ + INTEL_UEVENT_EXTRA_REG(c, \ + MSR_PEBS_LD_LAT_THRESHOLD, \ + 0xffff, \ + LDLAT) + #define EVENT_EXTRA_END EVENT_EXTRA_REG(0, 0, 0, 0, RSP_0) union perf_capabilities { @@ -355,8 +381,10 @@ struct x86_pmu { */ int attr_rdpmc; struct attribute **format_attrs; + struct attribute **event_attrs; ssize_t (*events_sysfs_show)(char *page, u64 config); + struct attribute **cpu_events; /* * CPU Hotplug hooks @@ -421,6 +449,23 @@ do { \ #define ERF_NO_HT_SHARING 1 #define ERF_HAS_RSP_1 2 +#define EVENT_VAR(_id) event_attr_##_id +#define EVENT_PTR(_id) &event_attr_##_id.attr.attr + +#define EVENT_ATTR(_name, _id) \ +static struct perf_pmu_events_attr EVENT_VAR(_id) = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = PERF_COUNT_HW_##_id, \ + .event_str = NULL, \ +}; + +#define EVENT_ATTR_STR(_name, v, str) \ +static struct perf_pmu_events_attr event_attr_##v = { \ + .attr = __ATTR(_name, 0444, events_sysfs_show, NULL), \ + .id = 0, \ + .event_str = str, \ +}; + extern struct x86_pmu x86_pmu __read_mostly; DECLARE_PER_CPU(struct cpu_hw_events, cpu_hw_events); @@ -628,6 +673,9 @@ int p6_pmu_init(void); int knc_pmu_init(void); +ssize_t events_sysfs_show(struct device *dev, struct device_attribute *attr, + char *page); + #else /* CONFIG_CPU_SUP_INTEL */ static inline void reserve_ds_buffers(void) diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c index dfdab42aed2..7e28d9467bb 100644 --- a/arch/x86/kernel/cpu/perf_event_amd.c +++ b/arch/x86/kernel/cpu/perf_event_amd.c @@ -132,14 +132,11 @@ static u64 amd_pmu_event_map(int hw_event) return amd_perfmon_event_map[hw_event]; } -static struct event_constraint *amd_nb_event_constraint; - /* * Previously calculated offsets */ static unsigned int event_offsets[X86_PMC_IDX_MAX] __read_mostly; static unsigned int count_offsets[X86_PMC_IDX_MAX] __read_mostly; -static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; /* * Legacy CPUs: @@ -147,14 +144,10 @@ static unsigned int rdpmc_indexes[X86_PMC_IDX_MAX] __read_mostly; * * CPUs with core performance counter extensions: * 6 counters starting at 0xc0010200 each offset by 2 - * - * CPUs with north bridge performance counter extensions: - * 4 additional counters starting at 0xc0010240 each offset by 2 - * (indexed right above either one of the above core counters) */ static inline int amd_pmu_addr_offset(int index, bool eventsel) { - int offset, first, base; + int offset; if (!index) return index; @@ -167,23 +160,7 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) if (offset) return offset; - if (amd_nb_event_constraint && - test_bit(index, amd_nb_event_constraint->idxmsk)) { - /* - * calculate the offset of NB counters with respect to - * base eventsel or perfctr - */ - - first = find_first_bit(amd_nb_event_constraint->idxmsk, - X86_PMC_IDX_MAX); - - if (eventsel) - base = MSR_F15H_NB_PERF_CTL - x86_pmu.eventsel; - else - base = MSR_F15H_NB_PERF_CTR - x86_pmu.perfctr; - - offset = base + ((index - first) << 1); - } else if (!cpu_has_perfctr_core) + if (!cpu_has_perfctr_core) offset = index; else offset = index << 1; @@ -196,36 +173,6 @@ static inline int amd_pmu_addr_offset(int index, bool eventsel) return offset; } -static inline int amd_pmu_rdpmc_index(int index) -{ - int ret, first; - - if (!index) - return index; - - ret = rdpmc_indexes[index]; - - if (ret) - return ret; - - if (amd_nb_event_constraint && - test_bit(index, amd_nb_event_constraint->idxmsk)) { - /* - * according to the mnual, ECX value of the NB counters is - * the index of the NB counter (0, 1, 2 or 3) plus 6 - */ - - first = find_first_bit(amd_nb_event_constraint->idxmsk, - X86_PMC_IDX_MAX); - ret = index - first + 6; - } else - ret = index; - - rdpmc_indexes[index] = ret; - - return ret; -} - static int amd_core_hw_config(struct perf_event *event) { if (event->attr.exclude_host && event->attr.exclude_guest) @@ -245,34 +192,6 @@ static int amd_core_hw_config(struct perf_event *event) } /* - * NB counters do not support the following event select bits: - * Host/Guest only - * Counter mask - * Invert counter mask - * Edge detect - * OS/User mode - */ -static int amd_nb_hw_config(struct perf_event *event) -{ - /* for NB, we only allow system wide counting mode */ - if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) - return -EINVAL; - - if (event->attr.exclude_user || event->attr.exclude_kernel || - event->attr.exclude_host || event->attr.exclude_guest) - return -EINVAL; - - event->hw.config &= ~(ARCH_PERFMON_EVENTSEL_USR | - ARCH_PERFMON_EVENTSEL_OS); - - if (event->hw.config & ~(AMD64_RAW_EVENT_MASK_NB | - ARCH_PERFMON_EVENTSEL_INT)) - return -EINVAL; - - return 0; -} - -/* * AMD64 events are detected based on their event codes. */ static inline unsigned int amd_get_event_code(struct hw_perf_event *hwc) @@ -285,11 +204,6 @@ static inline int amd_is_nb_event(struct hw_perf_event *hwc) return (hwc->config & 0xe0) == 0xe0; } -static inline int amd_is_perfctr_nb_event(struct hw_perf_event *hwc) -{ - return amd_nb_event_constraint && amd_is_nb_event(hwc); -} - static inline int amd_has_nb(struct cpu_hw_events *cpuc) { struct amd_nb *nb = cpuc->amd_nb; @@ -315,9 +229,6 @@ static int amd_pmu_hw_config(struct perf_event *event) if (event->attr.type == PERF_TYPE_RAW) event->hw.config |= event->attr.config & AMD64_RAW_EVENT_MASK; - if (amd_is_perfctr_nb_event(&event->hw)) - return amd_nb_hw_config(event); - return amd_core_hw_config(event); } @@ -341,19 +252,6 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc, } } -static void amd_nb_interrupt_hw_config(struct hw_perf_event *hwc) -{ - int core_id = cpu_data(smp_processor_id()).cpu_core_id; - - /* deliver interrupts only to this core */ - if (hwc->config & ARCH_PERFMON_EVENTSEL_INT) { - hwc->config |= AMD64_EVENTSEL_INT_CORE_ENABLE; - hwc->config &= ~AMD64_EVENTSEL_INT_CORE_SEL_MASK; - hwc->config |= (u64)(core_id) << - AMD64_EVENTSEL_INT_CORE_SEL_SHIFT; - } -} - /* * AMD64 NorthBridge events need special treatment because * counter access needs to be synchronized across all cores @@ -441,9 +339,6 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev if (new == -1) return &emptyconstraint; - if (amd_is_perfctr_nb_event(hwc)) - amd_nb_interrupt_hw_config(hwc); - return &nb->event_constraints[new]; } @@ -543,8 +438,7 @@ amd_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (!(amd_has_nb(cpuc) && amd_is_nb_event(&event->hw))) return &unconstrained; - return __amd_get_nb_event_constraints(cpuc, event, - amd_nb_event_constraint); + return __amd_get_nb_event_constraints(cpuc, event, NULL); } static void amd_put_event_constraints(struct cpu_hw_events *cpuc, @@ -643,9 +537,6 @@ static struct event_constraint amd_f15_PMC30 = EVENT_CONSTRAINT_OVERLAP(0, 0x09, static struct event_constraint amd_f15_PMC50 = EVENT_CONSTRAINT(0, 0x3F, 0); static struct event_constraint amd_f15_PMC53 = EVENT_CONSTRAINT(0, 0x38, 0); -static struct event_constraint amd_NBPMC96 = EVENT_CONSTRAINT(0, 0x3C0, 0); -static struct event_constraint amd_NBPMC74 = EVENT_CONSTRAINT(0, 0xF0, 0); - static struct event_constraint * amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *event) { @@ -711,8 +602,8 @@ amd_get_event_constraints_f15h(struct cpu_hw_events *cpuc, struct perf_event *ev return &amd_f15_PMC20; } case AMD_EVENT_NB: - return __amd_get_nb_event_constraints(cpuc, event, - amd_nb_event_constraint); + /* moved to perf_event_amd_uncore.c */ + return &emptyconstraint; default: return &emptyconstraint; } @@ -738,7 +629,6 @@ static __initconst const struct x86_pmu amd_pmu = { .eventsel = MSR_K7_EVNTSEL0, .perfctr = MSR_K7_PERFCTR0, .addr_offset = amd_pmu_addr_offset, - .rdpmc_index = amd_pmu_rdpmc_index, .event_map = amd_pmu_event_map, .max_events = ARRAY_SIZE(amd_perfmon_event_map), .num_counters = AMD64_NUM_COUNTERS, @@ -790,23 +680,6 @@ static int setup_perfctr_core(void) return 0; } -static int setup_perfctr_nb(void) -{ - if (!cpu_has_perfctr_nb) - return -ENODEV; - - x86_pmu.num_counters += AMD64_NUM_COUNTERS_NB; - - if (cpu_has_perfctr_core) - amd_nb_event_constraint = &amd_NBPMC96; - else - amd_nb_event_constraint = &amd_NBPMC74; - - printk(KERN_INFO "perf: AMD northbridge performance counters detected\n"); - - return 0; -} - __init int amd_pmu_init(void) { /* Performance-monitoring supported from K7 and later: */ @@ -817,7 +690,6 @@ __init int amd_pmu_init(void) setup_event_constraints(); setup_perfctr_core(); - setup_perfctr_nb(); /* Events are common for all AMDs */ memcpy(hw_cache_event_ids, amd_hw_cache_event_ids, diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c new file mode 100644 index 00000000000..c0c661adf03 --- /dev/null +++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c @@ -0,0 +1,547 @@ +/* + * Copyright (C) 2013 Advanced Micro Devices, Inc. + * + * Author: Jacob Shin <jacob.shin@amd.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + */ + +#include <linux/perf_event.h> +#include <linux/percpu.h> +#include <linux/types.h> +#include <linux/slab.h> +#include <linux/init.h> +#include <linux/cpu.h> +#include <linux/cpumask.h> + +#include <asm/cpufeature.h> +#include <asm/perf_event.h> +#include <asm/msr.h> + +#define NUM_COUNTERS_NB 4 +#define NUM_COUNTERS_L2 4 +#define MAX_COUNTERS NUM_COUNTERS_NB + +#define RDPMC_BASE_NB 6 +#define RDPMC_BASE_L2 10 + +#define COUNTER_SHIFT 16 + +struct amd_uncore { + int id; + int refcnt; + int cpu; + int num_counters; + int rdpmc_base; + u32 msr_base; + cpumask_t *active_mask; + struct pmu *pmu; + struct perf_event *events[MAX_COUNTERS]; + struct amd_uncore *free_when_cpu_online; +}; + +static struct amd_uncore * __percpu *amd_uncore_nb; +static struct amd_uncore * __percpu *amd_uncore_l2; + +static struct pmu amd_nb_pmu; +static struct pmu amd_l2_pmu; + +static cpumask_t amd_nb_active_mask; +static cpumask_t amd_l2_active_mask; + +static bool is_nb_event(struct perf_event *event) +{ + return event->pmu->type == amd_nb_pmu.type; +} + +static bool is_l2_event(struct perf_event *event) +{ + return event->pmu->type == amd_l2_pmu.type; +} + +static struct amd_uncore *event_to_amd_uncore(struct perf_event *event) +{ + if (is_nb_event(event) && amd_uncore_nb) + return *per_cpu_ptr(amd_uncore_nb, event->cpu); + else if (is_l2_event(event) && amd_uncore_l2) + return *per_cpu_ptr(amd_uncore_l2, event->cpu); + + return NULL; +} + +static void amd_uncore_read(struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + u64 prev, new; + s64 delta; + + /* + * since we do not enable counter overflow interrupts, + * we do not have to worry about prev_count changing on us + */ + + prev = local64_read(&hwc->prev_count); + rdpmcl(hwc->event_base_rdpmc, new); + local64_set(&hwc->prev_count, new); + delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT); + delta >>= COUNTER_SHIFT; + local64_add(delta, &event->count); +} + +static void amd_uncore_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + if (flags & PERF_EF_RELOAD) + wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count)); + + hwc->state = 0; + wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE)); + perf_event_update_userpage(event); +} + +static void amd_uncore_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hwc = &event->hw; + + wrmsrl(hwc->config_base, hwc->config); + hwc->state |= PERF_HES_STOPPED; + + if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) { + amd_uncore_read(event); + hwc->state |= PERF_HES_UPTODATE; + } +} + +static int amd_uncore_add(struct perf_event *event, int flags) +{ + int i; + struct amd_uncore *uncore = event_to_amd_uncore(event); + struct hw_perf_event *hwc = &event->hw; + + /* are we already assigned? */ + if (hwc->idx != -1 && uncore->events[hwc->idx] == event) + goto out; + + for (i = 0; i < uncore->num_counters; i++) { + if (uncore->events[i] == event) { + hwc->idx = i; + goto out; + } + } + + /* if not, take the first available counter */ + hwc->idx = -1; + for (i = 0; i < uncore->num_counters; i++) { + if (cmpxchg(&uncore->events[i], NULL, event) == NULL) { + hwc->idx = i; + break; + } + } + +out: + if (hwc->idx == -1) + return -EBUSY; + + hwc->config_base = uncore->msr_base + (2 * hwc->idx); + hwc->event_base = uncore->msr_base + 1 + (2 * hwc->idx); + hwc->event_base_rdpmc = uncore->rdpmc_base + hwc->idx; + hwc->state = PERF_HES_UPTODATE | PERF_HES_STOPPED; + + if (flags & PERF_EF_START) + amd_uncore_start(event, PERF_EF_RELOAD); + + return 0; +} + +static void amd_uncore_del(struct perf_event *event, int flags) +{ + int i; + struct amd_uncore *uncore = event_to_amd_uncore(event); + struct hw_perf_event *hwc = &event->hw; + + amd_uncore_stop(event, PERF_EF_UPDATE); + + for (i = 0; i < uncore->num_counters; i++) { + if (cmpxchg(&uncore->events[i], event, NULL) == event) + break; + } + + hwc->idx = -1; +} + +static int amd_uncore_event_init(struct perf_event *event) +{ + struct amd_uncore *uncore; + struct hw_perf_event *hwc = &event->hw; + + if (event->attr.type != event->pmu->type) + return -ENOENT; + + /* + * NB and L2 counters (MSRs) are shared across all cores that share the + * same NB / L2 cache. Interrupts can be directed to a single target + * core, however, event counts generated by processes running on other + * cores cannot be masked out. So we do not support sampling and + * per-thread events. + */ + if (is_sampling_event(event) || event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + /* NB and L2 counters do not have usr/os/guest/host bits */ + if (event->attr.exclude_user || event->attr.exclude_kernel || + event->attr.exclude_host || event->attr.exclude_guest) + return -EINVAL; + + /* and we do not enable counter overflow interrupts */ + hwc->config = event->attr.config & AMD64_RAW_EVENT_MASK_NB; + hwc->idx = -1; + + if (event->cpu < 0) + return -EINVAL; + + uncore = event_to_amd_uncore(event); + if (!uncore) + return -ENODEV; + + /* + * since request can come in to any of the shared cores, we will remap + * to a single common cpu. + */ + event->cpu = uncore->cpu; + + return 0; +} + +static ssize_t amd_uncore_attr_show_cpumask(struct device *dev, + struct device_attribute *attr, + char *buf) +{ + int n; + cpumask_t *active_mask; + struct pmu *pmu = dev_get_drvdata(dev); + + if (pmu->type == amd_nb_pmu.type) + active_mask = &amd_nb_active_mask; + else if (pmu->type == amd_l2_pmu.type) + active_mask = &amd_l2_active_mask; + else + return 0; + + n = cpulist_scnprintf(buf, PAGE_SIZE - 2, active_mask); + buf[n++] = '\n'; + buf[n] = '\0'; + return n; +} +static DEVICE_ATTR(cpumask, S_IRUGO, amd_uncore_attr_show_cpumask, NULL); + +static struct attribute *amd_uncore_attrs[] = { + &dev_attr_cpumask.attr, + NULL, +}; + +static struct attribute_group amd_uncore_attr_group = { + .attrs = amd_uncore_attrs, +}; + +PMU_FORMAT_ATTR(event, "config:0-7,32-35"); +PMU_FORMAT_ATTR(umask, "config:8-15"); + +static struct attribute *amd_uncore_format_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + NULL, +}; + +static struct attribute_group amd_uncore_format_group = { + .name = "format", + .attrs = amd_uncore_format_attr, +}; + +static const struct attribute_group *amd_uncore_attr_groups[] = { + &amd_uncore_attr_group, + &amd_uncore_format_group, + NULL, +}; + +static struct pmu amd_nb_pmu = { + .attr_groups = amd_uncore_attr_groups, + .name = "amd_nb", + .event_init = amd_uncore_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, +}; + +static struct pmu amd_l2_pmu = { + .attr_groups = amd_uncore_attr_groups, + .name = "amd_l2", + .event_init = amd_uncore_event_init, + .add = amd_uncore_add, + .del = amd_uncore_del, + .start = amd_uncore_start, + .stop = amd_uncore_stop, + .read = amd_uncore_read, +}; + +static struct amd_uncore * __cpuinit amd_uncore_alloc(unsigned int cpu) +{ + return kzalloc_node(sizeof(struct amd_uncore), GFP_KERNEL, + cpu_to_node(cpu)); +} + +static void __cpuinit amd_uncore_cpu_up_prepare(unsigned int cpu) +{ + struct amd_uncore *uncore; + + if (amd_uncore_nb) { + uncore = amd_uncore_alloc(cpu); + uncore->cpu = cpu; + uncore->num_counters = NUM_COUNTERS_NB; + uncore->rdpmc_base = RDPMC_BASE_NB; + uncore->msr_base = MSR_F15H_NB_PERF_CTL; + uncore->active_mask = &amd_nb_active_mask; + uncore->pmu = &amd_nb_pmu; + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + } + + if (amd_uncore_l2) { + uncore = amd_uncore_alloc(cpu); + uncore->cpu = cpu; + uncore->num_counters = NUM_COUNTERS_L2; + uncore->rdpmc_base = RDPMC_BASE_L2; + uncore->msr_base = MSR_F16H_L2I_PERF_CTL; + uncore->active_mask = &amd_l2_active_mask; + uncore->pmu = &amd_l2_pmu; + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + } +} + +static struct amd_uncore * +__cpuinit amd_uncore_find_online_sibling(struct amd_uncore *this, + struct amd_uncore * __percpu *uncores) +{ + unsigned int cpu; + struct amd_uncore *that; + + for_each_online_cpu(cpu) { + that = *per_cpu_ptr(uncores, cpu); + + if (!that) + continue; + + if (this == that) + continue; + + if (this->id == that->id) { + that->free_when_cpu_online = this; + this = that; + break; + } + } + + this->refcnt++; + return this; +} + +static void __cpuinit amd_uncore_cpu_starting(unsigned int cpu) +{ + unsigned int eax, ebx, ecx, edx; + struct amd_uncore *uncore; + + if (amd_uncore_nb) { + uncore = *per_cpu_ptr(amd_uncore_nb, cpu); + cpuid(0x8000001e, &eax, &ebx, &ecx, &edx); + uncore->id = ecx & 0xff; + + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_nb); + *per_cpu_ptr(amd_uncore_nb, cpu) = uncore; + } + + if (amd_uncore_l2) { + unsigned int apicid = cpu_data(cpu).apicid; + unsigned int nshared; + + uncore = *per_cpu_ptr(amd_uncore_l2, cpu); + cpuid_count(0x8000001d, 2, &eax, &ebx, &ecx, &edx); + nshared = ((eax >> 14) & 0xfff) + 1; + uncore->id = apicid - (apicid % nshared); + + uncore = amd_uncore_find_online_sibling(uncore, amd_uncore_l2); + *per_cpu_ptr(amd_uncore_l2, cpu) = uncore; + } +} + +static void __cpuinit uncore_online(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + + kfree(uncore->free_when_cpu_online); + uncore->free_when_cpu_online = NULL; + + if (cpu == uncore->cpu) + cpumask_set_cpu(cpu, uncore->active_mask); +} + +static void __cpuinit amd_uncore_cpu_online(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_online(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_online(cpu, amd_uncore_l2); +} + +static void __cpuinit uncore_down_prepare(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + unsigned int i; + struct amd_uncore *this = *per_cpu_ptr(uncores, cpu); + + if (this->cpu != cpu) + return; + + /* this cpu is going down, migrate to a shared sibling if possible */ + for_each_online_cpu(i) { + struct amd_uncore *that = *per_cpu_ptr(uncores, i); + + if (cpu == i) + continue; + + if (this == that) { + perf_pmu_migrate_context(this->pmu, cpu, i); + cpumask_clear_cpu(cpu, that->active_mask); + cpumask_set_cpu(i, that->active_mask); + that->cpu = i; + break; + } + } +} + +static void __cpuinit amd_uncore_cpu_down_prepare(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_down_prepare(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_down_prepare(cpu, amd_uncore_l2); +} + +static void __cpuinit uncore_dead(unsigned int cpu, + struct amd_uncore * __percpu *uncores) +{ + struct amd_uncore *uncore = *per_cpu_ptr(uncores, cpu); + + if (cpu == uncore->cpu) + cpumask_clear_cpu(cpu, uncore->active_mask); + + if (!--uncore->refcnt) + kfree(uncore); + *per_cpu_ptr(amd_uncore_nb, cpu) = NULL; +} + +static void __cpuinit amd_uncore_cpu_dead(unsigned int cpu) +{ + if (amd_uncore_nb) + uncore_dead(cpu, amd_uncore_nb); + + if (amd_uncore_l2) + uncore_dead(cpu, amd_uncore_l2); +} + +static int __cpuinit +amd_uncore_cpu_notifier(struct notifier_block *self, unsigned long action, + void *hcpu) +{ + unsigned int cpu = (long)hcpu; + + switch (action & ~CPU_TASKS_FROZEN) { + case CPU_UP_PREPARE: + amd_uncore_cpu_up_prepare(cpu); + break; + + case CPU_STARTING: + amd_uncore_cpu_starting(cpu); + break; + + case CPU_ONLINE: + amd_uncore_cpu_online(cpu); + break; + + case CPU_DOWN_PREPARE: + amd_uncore_cpu_down_prepare(cpu); + break; + + case CPU_UP_CANCELED: + case CPU_DEAD: + amd_uncore_cpu_dead(cpu); + break; + + default: + break; + } + + return NOTIFY_OK; +} + +static struct notifier_block amd_uncore_cpu_notifier_block __cpuinitdata = { + .notifier_call = amd_uncore_cpu_notifier, + .priority = CPU_PRI_PERF + 1, +}; + +static void __init init_cpu_already_online(void *dummy) +{ + unsigned int cpu = smp_processor_id(); + + amd_uncore_cpu_starting(cpu); + amd_uncore_cpu_online(cpu); +} + +static int __init amd_uncore_init(void) +{ + unsigned int cpu; + int ret = -ENODEV; + + if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) + return -ENODEV; + + if (!cpu_has_topoext) + return -ENODEV; + + if (cpu_has_perfctr_nb) { + amd_uncore_nb = alloc_percpu(struct amd_uncore *); + perf_pmu_register(&amd_nb_pmu, amd_nb_pmu.name, -1); + + printk(KERN_INFO "perf: AMD NB counters detected\n"); + ret = 0; + } + + if (cpu_has_perfctr_l2) { + amd_uncore_l2 = alloc_percpu(struct amd_uncore *); + perf_pmu_register(&amd_l2_pmu, amd_l2_pmu.name, -1); + + printk(KERN_INFO "perf: AMD L2I counters detected\n"); + ret = 0; + } + + if (ret) + return -ENODEV; + + get_online_cpus(); + /* init cpus already online before registering for hotplug notifier */ + for_each_online_cpu(cpu) { + amd_uncore_cpu_up_prepare(cpu); + smp_call_function_single(cpu, init_cpu_already_online, NULL, 1); + } + + register_cpu_notifier(&amd_uncore_cpu_notifier_block); + put_online_cpus(); + + return 0; +} +device_initcall(amd_uncore_init); diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index 529c8931fc0..f60d41ff9a9 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -81,6 +81,7 @@ static struct event_constraint intel_nehalem_event_constraints[] __read_mostly = static struct extra_reg intel_nehalem_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -101,9 +102,15 @@ static struct event_constraint intel_snb_event_constraints[] __read_mostly = FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* CPU_CLK_UNHALTED.REF */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ + INTEL_UEVENT_CONSTRAINT(0x05a3, 0xf), /* CYCLE_ACTIVITY.STALLS_L2_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ + INTEL_UEVENT_CONSTRAINT(0x06a3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_EVENT_CONSTRAINT(0x48, 0x4), /* L1D_PEND_MISS.PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ + INTEL_UEVENT_CONSTRAINT(0x04a3, 0xf), /* CYCLE_ACTIVITY.CYCLES_NO_DISPATCH */ + INTEL_UEVENT_CONSTRAINT(0x02a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ EVENT_CONSTRAINT_END }; @@ -121,10 +128,15 @@ static struct event_constraint intel_ivb_event_constraints[] __read_mostly = INTEL_UEVENT_CONSTRAINT(0x08a3, 0x4), /* CYCLE_ACTIVITY.CYCLES_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x0ca3, 0x4), /* CYCLE_ACTIVITY.STALLS_L1D_PENDING */ INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PREC_DIST */ - INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xd3, 0xf), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ + /* + * Errata BV98 -- MEM_*_RETIRED events can leak between counters of SMT + * siblings; disable these events because they can corrupt unrelated + * counters. + */ + INTEL_EVENT_CONSTRAINT(0xd0, 0x0), /* MEM_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd1, 0x0), /* MEM_LOAD_UOPS_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd2, 0x0), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ + INTEL_EVENT_CONSTRAINT(0xd3, 0x0), /* MEM_LOAD_UOPS_LLC_MISS_RETIRED.* */ EVENT_CONSTRAINT_END }; @@ -132,6 +144,7 @@ static struct extra_reg intel_westmere_extra_regs[] __read_mostly = { INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0xffff, RSP_0), INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0xffff, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x100b), EVENT_EXTRA_END }; @@ -149,11 +162,34 @@ static struct event_constraint intel_gen_event_constraints[] __read_mostly = }; static struct extra_reg intel_snb_extra_regs[] __read_mostly = { - INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffffffffull, RSP_0), - INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffffffffull, RSP_1), + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3f807f8fffull, RSP_1), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + INTEL_UEVENT_PEBS_LDLAT_EXTRA_REG(0x01cd), + EVENT_EXTRA_END +}; + +static struct extra_reg intel_snbep_extra_regs[] __read_mostly = { + INTEL_EVENT_EXTRA_REG(0xb7, MSR_OFFCORE_RSP_0, 0x3fffff8fffull, RSP_0), + INTEL_EVENT_EXTRA_REG(0xbb, MSR_OFFCORE_RSP_1, 0x3fffff8fffull, RSP_1), EVENT_EXTRA_END }; +EVENT_ATTR_STR(mem-loads, mem_ld_nhm, "event=0x0b,umask=0x10,ldlat=3"); +EVENT_ATTR_STR(mem-loads, mem_ld_snb, "event=0xcd,umask=0x1,ldlat=3"); +EVENT_ATTR_STR(mem-stores, mem_st_snb, "event=0xcd,umask=0x2"); + +struct attribute *nhm_events_attrs[] = { + EVENT_PTR(mem_ld_nhm), + NULL, +}; + +struct attribute *snb_events_attrs[] = { + EVENT_PTR(mem_ld_snb), + EVENT_PTR(mem_st_snb), + NULL, +}; + static u64 intel_pmu_event_map(int hw_event) { return intel_perfmon_event_map[hw_event]; @@ -1388,8 +1424,11 @@ x86_get_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) if (x86_pmu.event_constraints) { for_each_event_constraint(c, x86_pmu.event_constraints) { - if ((event->hw.config & c->cmask) == c->code) + if ((event->hw.config & c->cmask) == c->code) { + /* hw.flags zeroed at initialization */ + event->hw.flags |= c->flags; return c; + } } } @@ -1434,6 +1473,7 @@ intel_put_shared_regs_event_constraints(struct cpu_hw_events *cpuc, static void intel_put_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *event) { + event->hw.flags = 0; intel_put_shared_regs_event_constraints(cpuc, event); } @@ -1757,6 +1797,8 @@ static void intel_pmu_flush_branch_stack(void) PMU_FORMAT_ATTR(offcore_rsp, "config1:0-63"); +PMU_FORMAT_ATTR(ldlat, "config1:0-15"); + static struct attribute *intel_arch3_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -1767,6 +1809,7 @@ static struct attribute *intel_arch3_formats_attr[] = { &format_attr_cmask.attr, &format_attr_offcore_rsp.attr, /* XXX do NHM/WSM + SNB breakout */ + &format_attr_ldlat.attr, /* PEBS load latency */ NULL, }; @@ -2027,6 +2070,8 @@ __init int intel_pmu_init(void) x86_pmu.enable_all = intel_pmu_nhm_enable_all; x86_pmu.extra_regs = intel_nehalem_extra_regs; + x86_pmu.cpu_events = nhm_events_attrs; + /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2070,6 +2115,8 @@ __init int intel_pmu_init(void) x86_pmu.extra_regs = intel_westmere_extra_regs; x86_pmu.er_flags |= ERF_HAS_RSP_1; + x86_pmu.cpu_events = nhm_events_attrs; + /* UOPS_ISSUED.STALLED_CYCLES */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2093,11 +2140,16 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_snb_event_constraints; x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 45) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.cpu_events = snb_events_attrs; + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); @@ -2119,11 +2171,16 @@ __init int intel_pmu_init(void) x86_pmu.event_constraints = intel_ivb_event_constraints; x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints; x86_pmu.pebs_aliases = intel_pebs_aliases_snb; - x86_pmu.extra_regs = intel_snb_extra_regs; + if (boot_cpu_data.x86_model == 62) + x86_pmu.extra_regs = intel_snbep_extra_regs; + else + x86_pmu.extra_regs = intel_snb_extra_regs; /* all extra regs are per-cpu when HT is on */ x86_pmu.er_flags |= ERF_HAS_RSP_1; x86_pmu.er_flags |= ERF_NO_HT_SHARING; + x86_pmu.cpu_events = snb_events_attrs; + /* UOPS_ISSUED.ANY,c=1,i=1 to count stall cycles */ intel_perfmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] = X86_CONFIG(.event=0x0e, .umask=0x01, .inv=1, .cmask=1); diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index b05a575d56f..60250f68705 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -24,6 +24,130 @@ struct pebs_record_32 { */ +union intel_x86_pebs_dse { + u64 val; + struct { + unsigned int ld_dse:4; + unsigned int ld_stlb_miss:1; + unsigned int ld_locked:1; + unsigned int ld_reserved:26; + }; + struct { + unsigned int st_l1d_hit:1; + unsigned int st_reserved1:3; + unsigned int st_stlb_miss:1; + unsigned int st_locked:1; + unsigned int st_reserved2:26; + }; +}; + + +/* + * Map PEBS Load Latency Data Source encodings to generic + * memory data source information + */ +#define P(a, b) PERF_MEM_S(a, b) +#define OP_LH (P(OP, LOAD) | P(LVL, HIT)) +#define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) + +static const u64 pebs_data_source[] = { + P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ + OP_LH | P(LVL, L1) | P(SNOOP, NONE), /* 0x01: L1 local */ + OP_LH | P(LVL, LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ + OP_LH | P(LVL, L2) | P(SNOOP, NONE), /* 0x03: L2 hit */ + OP_LH | P(LVL, L3) | P(SNOOP, NONE), /* 0x04: L3 hit */ + OP_LH | P(LVL, L3) | P(SNOOP, MISS), /* 0x05: L3 hit, snoop miss */ + OP_LH | P(LVL, L3) | P(SNOOP, HIT), /* 0x06: L3 hit, snoop hit */ + OP_LH | P(LVL, L3) | P(SNOOP, HITM), /* 0x07: L3 hit, snoop hitm */ + OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HIT), /* 0x08: L3 miss snoop hit */ + OP_LH | P(LVL, REM_CCE1) | P(SNOOP, HITM), /* 0x09: L3 miss snoop hitm*/ + OP_LH | P(LVL, LOC_RAM) | P(SNOOP, HIT), /* 0x0a: L3 miss, shared */ + OP_LH | P(LVL, REM_RAM1) | P(SNOOP, HIT), /* 0x0b: L3 miss, shared */ + OP_LH | P(LVL, LOC_RAM) | SNOOP_NONE_MISS,/* 0x0c: L3 miss, excl */ + OP_LH | P(LVL, REM_RAM1) | SNOOP_NONE_MISS,/* 0x0d: L3 miss, excl */ + OP_LH | P(LVL, IO) | P(SNOOP, NONE), /* 0x0e: I/O */ + OP_LH | P(LVL, UNC) | P(SNOOP, NONE), /* 0x0f: uncached */ +}; + +static u64 precise_store_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val = P(OP, STORE) | P(SNOOP, NA) | P(LVL, L1) | P(TLB, L2); + + dse.val = status; + + /* + * bit 4: TLB access + * 1 = stored missed 2nd level TLB + * + * so it either hit the walker or the OS + * otherwise hit 2nd level TLB + */ + if (dse.st_stlb_miss) + val |= P(TLB, MISS); + else + val |= P(TLB, HIT); + + /* + * bit 0: hit L1 data cache + * if not set, then all we know is that + * it missed L1D + */ + if (dse.st_l1d_hit) + val |= P(LVL, HIT); + else + val |= P(LVL, MISS); + + /* + * bit 5: Locked prefix + */ + if (dse.st_locked) + val |= P(LOCK, LOCKED); + + return val; +} + +static u64 load_latency_data(u64 status) +{ + union intel_x86_pebs_dse dse; + u64 val; + int model = boot_cpu_data.x86_model; + int fam = boot_cpu_data.x86; + + dse.val = status; + + /* + * use the mapping table for bit 0-3 + */ + val = pebs_data_source[dse.ld_dse]; + + /* + * Nehalem models do not support TLB, Lock infos + */ + if (fam == 0x6 && (model == 26 || model == 30 + || model == 31 || model == 46)) { + val |= P(TLB, NA) | P(LOCK, NA); + return val; + } + /* + * bit 4: TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (dse.ld_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* + * bit 5: locked prefix + */ + if (dse.ld_locked) + val |= P(LOCK, LOCKED); + + return val; +} + struct pebs_record_core { u64 flags, ip; u64 ax, bx, cx, dx; @@ -314,10 +438,11 @@ int intel_pmu_drain_bts_buffer(void) if (top <= at) return 0; + memset(®s, 0, sizeof(regs)); + ds->bts_index = ds->bts_buffer_base; perf_sample_data_init(&data, 0, event->hw.last_period); - regs.ip = 0; /* * Prepare a generic sample, i.e. fill in the invariant fields. @@ -364,7 +489,7 @@ struct event_constraint intel_atom_pebs_event_constraints[] = { }; struct event_constraint intel_nehalem_pebs_event_constraints[] = { - INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INST_RETIRED.ANY */ @@ -379,7 +504,7 @@ struct event_constraint intel_nehalem_pebs_event_constraints[] = { }; struct event_constraint intel_westmere_pebs_event_constraints[] = { - INTEL_EVENT_CONSTRAINT(0x0b, 0xf), /* MEM_INST_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x100b, 0xf), /* MEM_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0x0f, 0xf), /* MEM_UNCORE_RETIRED.* */ INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */ INTEL_EVENT_CONSTRAINT(0xc0, 0xf), /* INSTR_RETIRED.* */ @@ -399,7 +524,8 @@ struct event_constraint intel_snb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ + INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -413,7 +539,8 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = { INTEL_UEVENT_CONSTRAINT(0x02c2, 0xf), /* UOPS_RETIRED.RETIRE_SLOTS */ INTEL_EVENT_CONSTRAINT(0xc4, 0xf), /* BR_INST_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xc5, 0xf), /* BR_MISP_RETIRED.* */ - INTEL_EVENT_CONSTRAINT(0xcd, 0x8), /* MEM_TRANS_RETIRED.* */ + INTEL_PLD_CONSTRAINT(0x01cd, 0x8), /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */ + INTEL_PST_CONSTRAINT(0x02cd, 0x8), /* MEM_TRANS_RETIRED.PRECISE_STORES */ INTEL_EVENT_CONSTRAINT(0xd0, 0xf), /* MEM_UOP_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd1, 0xf), /* MEM_LOAD_UOPS_RETIRED.* */ INTEL_EVENT_CONSTRAINT(0xd2, 0xf), /* MEM_LOAD_UOPS_LLC_HIT_RETIRED.* */ @@ -430,8 +557,10 @@ struct event_constraint *intel_pebs_constraints(struct perf_event *event) if (x86_pmu.pebs_constraints) { for_each_event_constraint(c, x86_pmu.pebs_constraints) { - if ((event->hw.config & c->cmask) == c->code) + if ((event->hw.config & c->cmask) == c->code) { + event->hw.flags |= c->flags; return c; + } } } @@ -446,6 +575,11 @@ void intel_pmu_pebs_enable(struct perf_event *event) hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; cpuc->pebs_enabled |= 1ULL << hwc->idx; + + if (event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) + cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); + else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST) + cpuc->pebs_enabled |= 1ULL << 63; } void intel_pmu_pebs_disable(struct perf_event *event) @@ -558,20 +692,51 @@ static void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, void *__pebs) { /* - * We cast to pebs_record_core since that is a subset of - * both formats and we don't use the other fields in this - * routine. + * We cast to pebs_record_nhm to get the load latency data + * if extra_reg MSR_PEBS_LD_LAT_THRESHOLD used */ struct cpu_hw_events *cpuc = &__get_cpu_var(cpu_hw_events); - struct pebs_record_core *pebs = __pebs; + struct pebs_record_nhm *pebs = __pebs; struct perf_sample_data data; struct pt_regs regs; + u64 sample_type; + int fll, fst; if (!intel_pmu_save_and_restart(event)) return; + fll = event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT; + fst = event->hw.flags & PERF_X86_EVENT_PEBS_ST; + perf_sample_data_init(&data, 0, event->hw.last_period); + data.period = event->hw.last_period; + sample_type = event->attr.sample_type; + + /* + * if PEBS-LL or PreciseStore + */ + if (fll || fst) { + if (sample_type & PERF_SAMPLE_ADDR) + data.addr = pebs->dla; + + /* + * Use latency for weight (only avail with PEBS-LL) + */ + if (fll && (sample_type & PERF_SAMPLE_WEIGHT)) + data.weight = pebs->lat; + + /* + * data.data_src encodes the data source + */ + if (sample_type & PERF_SAMPLE_DATA_SRC) { + if (fll) + data.data_src.val = load_latency_data(pebs->dse); + else + data.data_src.val = precise_store_data(pebs->dse); + } + } + /* * We use the interrupt regs as a base because the PEBS record * does not contain a full regs set, specifically it seems to diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c index da02e9cc375..d978353c939 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c +++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c @@ -310,7 +310,7 @@ void intel_pmu_lbr_read(void) * - in case there is no HW filter * - in case the HW filter has errata or limitations */ -static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) +static int intel_pmu_setup_sw_lbr_filter(struct perf_event *event) { u64 br_type = event->attr.branch_sample_type; int mask = 0; @@ -318,8 +318,11 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) if (br_type & PERF_SAMPLE_BRANCH_USER) mask |= X86_BR_USER; - if (br_type & PERF_SAMPLE_BRANCH_KERNEL) + if (br_type & PERF_SAMPLE_BRANCH_KERNEL) { + if (perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) + return -EACCES; mask |= X86_BR_KERNEL; + } /* we ignore BRANCH_HV here */ @@ -339,6 +342,8 @@ static void intel_pmu_setup_sw_lbr_filter(struct perf_event *event) * be used by fixup code for some CPU */ event->hw.branch_reg.reg = mask; + + return 0; } /* @@ -386,7 +391,9 @@ int intel_pmu_setup_lbr_filter(struct perf_event *event) /* * setup SW LBR filter */ - intel_pmu_setup_sw_lbr_filter(event); + ret = intel_pmu_setup_sw_lbr_filter(event); + if (ret) + return ret; /* * setup HW LBR filter, if any @@ -442,8 +449,18 @@ static int branch_type(unsigned long from, unsigned long to) return X86_BR_NONE; addr = buf; - } else - addr = (void *)from; + } else { + /* + * The LBR logs any address in the IP, even if the IP just + * faulted. This means userspace can control the from address. + * Ensure we don't blindy read any address by validating it is + * a known text address. + */ + if (kernel_text_address(from)) + addr = (void *)from; + else + return X86_BR_NONE; + } /* * decoder needs to know the ABI especially diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c index b43200dbfe7..52441a2af53 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c @@ -17,6 +17,9 @@ static struct event_constraint constraint_fixed = static struct event_constraint constraint_empty = EVENT_CONSTRAINT(0, 0, 0); +#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ + ((1ULL << (n)) - 1))) + DEFINE_UNCORE_FORMAT_ATTR(event, event, "config:0-7"); DEFINE_UNCORE_FORMAT_ATTR(event_ext, event, "config:0-7,21"); DEFINE_UNCORE_FORMAT_ATTR(umask, umask, "config:8-15"); @@ -31,9 +34,13 @@ DEFINE_UNCORE_FORMAT_ATTR(occ_sel, occ_sel, "config:14-15"); DEFINE_UNCORE_FORMAT_ATTR(occ_invert, occ_invert, "config:30"); DEFINE_UNCORE_FORMAT_ATTR(occ_edge, occ_edge, "config:14-51"); DEFINE_UNCORE_FORMAT_ATTR(filter_tid, filter_tid, "config1:0-4"); +DEFINE_UNCORE_FORMAT_ATTR(filter_link, filter_link, "config1:5-8"); DEFINE_UNCORE_FORMAT_ATTR(filter_nid, filter_nid, "config1:10-17"); +DEFINE_UNCORE_FORMAT_ATTR(filter_nid2, filter_nid, "config1:32-47"); DEFINE_UNCORE_FORMAT_ATTR(filter_state, filter_state, "config1:18-22"); +DEFINE_UNCORE_FORMAT_ATTR(filter_state2, filter_state, "config1:17-22"); DEFINE_UNCORE_FORMAT_ATTR(filter_opc, filter_opc, "config1:23-31"); +DEFINE_UNCORE_FORMAT_ATTR(filter_opc2, filter_opc, "config1:52-60"); DEFINE_UNCORE_FORMAT_ATTR(filter_band0, filter_band0, "config1:0-7"); DEFINE_UNCORE_FORMAT_ATTR(filter_band1, filter_band1, "config1:8-15"); DEFINE_UNCORE_FORMAT_ATTR(filter_band2, filter_band2, "config1:16-23"); @@ -110,6 +117,21 @@ static void uncore_put_constraint(struct intel_uncore_box *box, struct perf_even reg1->alloc = 0; } +static u64 uncore_shared_reg_config(struct intel_uncore_box *box, int idx) +{ + struct intel_uncore_extra_reg *er; + unsigned long flags; + u64 config; + + er = &box->shared_regs[idx]; + + raw_spin_lock_irqsave(&er->lock, flags); + config = er->config; + raw_spin_unlock_irqrestore(&er->lock, flags); + + return config; +} + /* Sandy Bridge-EP uncore support */ static struct intel_uncore_type snbep_uncore_cbox; static struct intel_uncore_type snbep_uncore_pcu; @@ -205,7 +227,7 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p struct hw_perf_event_extra *reg1 = &hwc->extra_reg; if (reg1->idx != EXTRA_REG_NONE) - wrmsrl(reg1->reg, reg1->config); + wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0)); wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); } @@ -226,29 +248,6 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box) wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT); } -static int snbep_uncore_hw_config(struct intel_uncore_box *box, struct perf_event *event) -{ - struct hw_perf_event *hwc = &event->hw; - struct hw_perf_event_extra *reg1 = &hwc->extra_reg; - - if (box->pmu->type == &snbep_uncore_cbox) { - reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + - SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; - reg1->config = event->attr.config1 & - SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK; - } else { - if (box->pmu->type == &snbep_uncore_pcu) { - reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; - reg1->config = event->attr.config1 & SNBEP_PCU_MSR_PMON_BOX_FILTER_MASK; - } else { - return 0; - } - } - reg1->idx = 0; - - return 0; -} - static struct attribute *snbep_uncore_formats_attr[] = { &format_attr_event.attr, &format_attr_umask.attr, @@ -345,16 +344,16 @@ static struct attribute_group snbep_uncore_qpi_format_group = { .attrs = snbep_uncore_qpi_formats_attr, }; +#define SNBEP_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = snbep_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + static struct intel_uncore_ops snbep_uncore_msr_ops = { - .init_box = snbep_uncore_msr_init_box, - .disable_box = snbep_uncore_msr_disable_box, - .enable_box = snbep_uncore_msr_enable_box, - .disable_event = snbep_uncore_msr_disable_event, - .enable_event = snbep_uncore_msr_enable_event, - .read_counter = uncore_msr_read_counter, - .get_constraint = uncore_get_constraint, - .put_constraint = uncore_put_constraint, - .hw_config = snbep_uncore_hw_config, + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), }; static struct intel_uncore_ops snbep_uncore_pci_ops = { @@ -372,6 +371,7 @@ static struct event_constraint snbep_uncore_cbox_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x04, 0x3), UNCORE_EVENT_CONSTRAINT(0x05, 0x3), UNCORE_EVENT_CONSTRAINT(0x07, 0x3), + UNCORE_EVENT_CONSTRAINT(0x09, 0x3), UNCORE_EVENT_CONSTRAINT(0x11, 0x1), UNCORE_EVENT_CONSTRAINT(0x12, 0x3), UNCORE_EVENT_CONSTRAINT(0x13, 0x3), @@ -421,6 +421,14 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x24, 0x3), UNCORE_EVENT_CONSTRAINT(0x25, 0x3), UNCORE_EVENT_CONSTRAINT(0x26, 0x3), + UNCORE_EVENT_CONSTRAINT(0x28, 0x3), + UNCORE_EVENT_CONSTRAINT(0x29, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2a, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2b, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2c, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2d, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2e, 0x3), + UNCORE_EVENT_CONSTRAINT(0x2f, 0x3), UNCORE_EVENT_CONSTRAINT(0x30, 0x3), UNCORE_EVENT_CONSTRAINT(0x31, 0x3), UNCORE_EVENT_CONSTRAINT(0x32, 0x3), @@ -428,6 +436,8 @@ static struct event_constraint snbep_uncore_r3qpi_constraints[] = { UNCORE_EVENT_CONSTRAINT(0x34, 0x3), UNCORE_EVENT_CONSTRAINT(0x36, 0x3), UNCORE_EVENT_CONSTRAINT(0x37, 0x3), + UNCORE_EVENT_CONSTRAINT(0x38, 0x3), + UNCORE_EVENT_CONSTRAINT(0x39, 0x3), EVENT_CONSTRAINT_END }; @@ -446,6 +456,145 @@ static struct intel_uncore_type snbep_uncore_ubox = { .format_group = &snbep_uncore_ubox_format_group, }; +static struct extra_reg snbep_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0x6), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x2), + EVENT_EXTRA_END +}; + +static void snbep_cbox_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i; + + if (uncore_box_is_fake(box)) + return; + + for (i = 0; i < 5; i++) { + if (reg1->alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + reg1->alloc = 0; +} + +static struct event_constraint * +__snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event, + u64 (*cbox_filter_mask)(int fields)) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + int i, alloc = 0; + unsigned long flags; + u64 mask; + + if (reg1->idx == EXTRA_REG_NONE) + return NULL; + + raw_spin_lock_irqsave(&er->lock, flags); + for (i = 0; i < 5; i++) { + if (!(reg1->idx & (0x1 << i))) + continue; + if (!uncore_box_is_fake(box) && (reg1->alloc & (0x1 << i))) + continue; + + mask = cbox_filter_mask(0x1 << i); + if (!__BITS_VALUE(atomic_read(&er->ref), i, 6) || + !((reg1->config ^ er->config) & mask)) { + atomic_add(1 << (i * 6), &er->ref); + er->config &= ~mask; + er->config |= reg1->config & mask; + alloc |= (0x1 << i); + } else { + break; + } + } + raw_spin_unlock_irqrestore(&er->lock, flags); + if (i < 5) + goto fail; + + if (!uncore_box_is_fake(box)) + reg1->alloc |= alloc; + + return 0; +fail: + for (; i >= 0; i--) { + if (alloc & (0x1 << i)) + atomic_sub(1 << (i * 6), &er->ref); + } + return &constraint_empty; +} + +static u64 snbep_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x4) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +snbep_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, snbep_cbox_filter_mask); +} + +static int snbep_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = snbep_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & snbep_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_cbox_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_cbox_hw_config, + .get_constraint = snbep_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + static struct intel_uncore_type snbep_uncore_cbox = { .name = "cbox", .num_counters = 4, @@ -458,10 +607,104 @@ static struct intel_uncore_type snbep_uncore_cbox = { .msr_offset = SNBEP_CBO_MSR_OFFSET, .num_shared_regs = 1, .constraints = snbep_uncore_cbox_constraints, - .ops = &snbep_uncore_msr_ops, + .ops = &snbep_uncore_cbox_ops, .format_group = &snbep_uncore_cbox_format_group, }; +static u64 snbep_pcu_alter_er(struct perf_event *event, int new_idx, bool modify) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + u64 config = reg1->config; + + if (new_idx > reg1->idx) + config <<= 8 * (new_idx - reg1->idx); + else + config >>= 8 * (reg1->idx - new_idx); + + if (modify) { + hwc->config += new_idx - reg1->idx; + reg1->config = config; + reg1->idx = new_idx; + } + return config; +} + +static struct event_constraint * +snbep_pcu_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + unsigned long flags; + int idx = reg1->idx; + u64 mask, config1 = reg1->config; + bool ok = false; + + if (reg1->idx == EXTRA_REG_NONE || + (!uncore_box_is_fake(box) && reg1->alloc)) + return NULL; +again: + mask = 0xff << (idx * 8); + raw_spin_lock_irqsave(&er->lock, flags); + if (!__BITS_VALUE(atomic_read(&er->ref), idx, 8) || + !((config1 ^ er->config) & mask)) { + atomic_add(1 << (idx * 8), &er->ref); + er->config &= ~mask; + er->config |= config1 & mask; + ok = true; + } + raw_spin_unlock_irqrestore(&er->lock, flags); + + if (!ok) { + idx = (idx + 1) % 4; + if (idx != reg1->idx) { + config1 = snbep_pcu_alter_er(event, idx, false); + goto again; + } + return &constraint_empty; + } + + if (!uncore_box_is_fake(box)) { + if (idx != reg1->idx) + snbep_pcu_alter_er(event, idx, true); + reg1->alloc = 1; + } + return NULL; +} + +static void snbep_pcu_put_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct intel_uncore_extra_reg *er = &box->shared_regs[0]; + + if (uncore_box_is_fake(box) || !reg1->alloc) + return; + + atomic_sub(1 << (reg1->idx * 8), &er->ref); + reg1->alloc = 0; +} + +static int snbep_pcu_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + int ev_sel = hwc->config & SNBEP_PMON_CTL_EV_SEL_MASK; + + if (ev_sel >= 0xb && ev_sel <= 0xe) { + reg1->reg = SNBEP_PCU_MSR_PMON_BOX_FILTER; + reg1->idx = ev_sel - 0xb; + reg1->config = event->attr.config1 & (0xff << reg1->idx); + } + return 0; +} + +static struct intel_uncore_ops snbep_uncore_pcu_ops = { + SNBEP_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + static struct intel_uncore_type snbep_uncore_pcu = { .name = "pcu", .num_counters = 4, @@ -472,7 +715,7 @@ static struct intel_uncore_type snbep_uncore_pcu = { .event_mask = SNBEP_PCU_MSR_PMON_RAW_EVENT_MASK, .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, .num_shared_regs = 1, - .ops = &snbep_uncore_msr_ops, + .ops = &snbep_uncore_pcu_ops, .format_group = &snbep_uncore_pcu_format_group, }; @@ -544,55 +787,63 @@ static struct intel_uncore_type snbep_uncore_r3qpi = { SNBEP_UNCORE_PCI_COMMON_INIT(), }; +enum { + SNBEP_PCI_UNCORE_HA, + SNBEP_PCI_UNCORE_IMC, + SNBEP_PCI_UNCORE_QPI, + SNBEP_PCI_UNCORE_R2PCIE, + SNBEP_PCI_UNCORE_R3QPI, +}; + static struct intel_uncore_type *snbep_pci_uncores[] = { - &snbep_uncore_ha, - &snbep_uncore_imc, - &snbep_uncore_qpi, - &snbep_uncore_r2pcie, - &snbep_uncore_r3qpi, + [SNBEP_PCI_UNCORE_HA] = &snbep_uncore_ha, + [SNBEP_PCI_UNCORE_IMC] = &snbep_uncore_imc, + [SNBEP_PCI_UNCORE_QPI] = &snbep_uncore_qpi, + [SNBEP_PCI_UNCORE_R2PCIE] = &snbep_uncore_r2pcie, + [SNBEP_PCI_UNCORE_R3QPI] = &snbep_uncore_r3qpi, NULL, }; static DEFINE_PCI_DEVICE_TABLE(snbep_uncore_pci_ids) = { { /* Home Agent */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_HA), - .driver_data = (unsigned long)&snbep_uncore_ha, + .driver_data = SNBEP_PCI_UNCORE_HA, }, { /* MC Channel 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC0), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC1), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 2 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC2), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* MC Channel 3 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_IMC3), - .driver_data = (unsigned long)&snbep_uncore_imc, + .driver_data = SNBEP_PCI_UNCORE_IMC, }, { /* QPI Port 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI0), - .driver_data = (unsigned long)&snbep_uncore_qpi, + .driver_data = SNBEP_PCI_UNCORE_QPI, }, { /* QPI Port 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_QPI1), - .driver_data = (unsigned long)&snbep_uncore_qpi, + .driver_data = SNBEP_PCI_UNCORE_QPI, }, - { /* P2PCIe */ + { /* R2PCIe */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R2PCIE), - .driver_data = (unsigned long)&snbep_uncore_r2pcie, + .driver_data = SNBEP_PCI_UNCORE_R2PCIE, }, { /* R3QPI Link 0 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI0), - .driver_data = (unsigned long)&snbep_uncore_r3qpi, + .driver_data = SNBEP_PCI_UNCORE_R3QPI, }, { /* R3QPI Link 1 */ PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_UNC_R3QPI1), - .driver_data = (unsigned long)&snbep_uncore_r3qpi, + .driver_data = SNBEP_PCI_UNCORE_R3QPI, }, { /* end: all zeroes */ } }; @@ -605,7 +856,7 @@ static struct pci_driver snbep_uncore_pci_driver = { /* * build pci bus to socket mapping */ -static int snbep_pci2phy_map_init(void) +static int snbep_pci2phy_map_init(int devid) { struct pci_dev *ubox_dev = NULL; int i, bus, nodeid; @@ -614,9 +865,7 @@ static int snbep_pci2phy_map_init(void) while (1) { /* find the UBOX device */ - ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, - PCI_DEVICE_ID_INTEL_JAKETOWN_UBOX, - ubox_dev); + ubox_dev = pci_get_device(PCI_VENDOR_ID_INTEL, devid, ubox_dev); if (!ubox_dev) break; bus = ubox_dev->bus->number; @@ -639,7 +888,7 @@ static int snbep_pci2phy_map_init(void) break; } } - }; + } if (ubox_dev) pci_dev_put(ubox_dev); @@ -648,6 +897,440 @@ static int snbep_pci2phy_map_init(void) } /* end of Sandy Bridge-EP uncore support */ +/* IvyTown uncore support */ +static void ivt_uncore_msr_init_box(struct intel_uncore_box *box) +{ + unsigned msr = uncore_msr_box_ctl(box); + if (msr) + wrmsrl(msr, IVT_PMON_BOX_CTL_INT); +} + +static void ivt_uncore_pci_init_box(struct intel_uncore_box *box) +{ + struct pci_dev *pdev = box->pci_dev; + + pci_write_config_dword(pdev, SNBEP_PCI_PMON_BOX_CTL, IVT_PMON_BOX_CTL_INT); +} + +#define IVT_UNCORE_MSR_OPS_COMMON_INIT() \ + .init_box = ivt_uncore_msr_init_box, \ + .disable_box = snbep_uncore_msr_disable_box, \ + .enable_box = snbep_uncore_msr_enable_box, \ + .disable_event = snbep_uncore_msr_disable_event, \ + .enable_event = snbep_uncore_msr_enable_event, \ + .read_counter = uncore_msr_read_counter + +static struct intel_uncore_ops ivt_uncore_msr_ops = { + IVT_UNCORE_MSR_OPS_COMMON_INIT(), +}; + +static struct intel_uncore_ops ivt_uncore_pci_ops = { + .init_box = ivt_uncore_pci_init_box, + .disable_box = snbep_uncore_pci_disable_box, + .enable_box = snbep_uncore_pci_enable_box, + .disable_event = snbep_uncore_pci_disable_event, + .enable_event = snbep_uncore_pci_enable_event, + .read_counter = snbep_uncore_pci_read_counter, +}; + +#define IVT_UNCORE_PCI_COMMON_INIT() \ + .perf_ctr = SNBEP_PCI_PMON_CTR0, \ + .event_ctl = SNBEP_PCI_PMON_CTL0, \ + .event_mask = IVT_PMON_RAW_EVENT_MASK, \ + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, \ + .ops = &ivt_uncore_pci_ops, \ + .format_group = &ivt_uncore_format_group + +static struct attribute *ivt_uncore_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute *ivt_uncore_ubox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_inv.attr, + &format_attr_thresh5.attr, + NULL, +}; + +static struct attribute *ivt_uncore_cbox_formats_attr[] = { + &format_attr_event.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_tid_en.attr, + &format_attr_thresh8.attr, + &format_attr_filter_tid.attr, + &format_attr_filter_link.attr, + &format_attr_filter_state2.attr, + &format_attr_filter_nid2.attr, + &format_attr_filter_opc2.attr, + NULL, +}; + +static struct attribute *ivt_uncore_pcu_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_occ_sel.attr, + &format_attr_edge.attr, + &format_attr_thresh5.attr, + &format_attr_occ_invert.attr, + &format_attr_occ_edge.attr, + &format_attr_filter_band0.attr, + &format_attr_filter_band1.attr, + &format_attr_filter_band2.attr, + &format_attr_filter_band3.attr, + NULL, +}; + +static struct attribute *ivt_uncore_qpi_formats_attr[] = { + &format_attr_event_ext.attr, + &format_attr_umask.attr, + &format_attr_edge.attr, + &format_attr_thresh8.attr, + NULL, +}; + +static struct attribute_group ivt_uncore_format_group = { + .name = "format", + .attrs = ivt_uncore_formats_attr, +}; + +static struct attribute_group ivt_uncore_ubox_format_group = { + .name = "format", + .attrs = ivt_uncore_ubox_formats_attr, +}; + +static struct attribute_group ivt_uncore_cbox_format_group = { + .name = "format", + .attrs = ivt_uncore_cbox_formats_attr, +}; + +static struct attribute_group ivt_uncore_pcu_format_group = { + .name = "format", + .attrs = ivt_uncore_pcu_formats_attr, +}; + +static struct attribute_group ivt_uncore_qpi_format_group = { + .name = "format", + .attrs = ivt_uncore_qpi_formats_attr, +}; + +static struct intel_uncore_type ivt_uncore_ubox = { + .name = "ubox", + .num_counters = 2, + .num_boxes = 1, + .perf_ctr_bits = 44, + .fixed_ctr_bits = 48, + .perf_ctr = SNBEP_U_MSR_PMON_CTR0, + .event_ctl = SNBEP_U_MSR_PMON_CTL0, + .event_mask = IVT_U_MSR_PMON_RAW_EVENT_MASK, + .fixed_ctr = SNBEP_U_MSR_PMON_UCLK_FIXED_CTR, + .fixed_ctl = SNBEP_U_MSR_PMON_UCLK_FIXED_CTL, + .ops = &ivt_uncore_msr_ops, + .format_group = &ivt_uncore_ubox_format_group, +}; + +static struct extra_reg ivt_uncore_cbox_extra_regs[] = { + SNBEP_CBO_EVENT_EXTRA_REG(SNBEP_CBO_PMON_CTL_TID_EN, + SNBEP_CBO_PMON_CTL_TID_EN, 0x1), + SNBEP_CBO_EVENT_EXTRA_REG(0x1031, 0x10ff, 0x2), + SNBEP_CBO_EVENT_EXTRA_REG(0x0334, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0534, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x0934, 0xffff, 0x4), + SNBEP_CBO_EVENT_EXTRA_REG(0x4134, 0xffff, 0xc), + SNBEP_CBO_EVENT_EXTRA_REG(0x0135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4135, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4335, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4435, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4835, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a35, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5035, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8135, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8335, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x0336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x2336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4136, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4336, 0xffff, 0x18), + SNBEP_CBO_EVENT_EXTRA_REG(0x4436, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4836, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x4a36, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x5036, 0xffff, 0x8), + SNBEP_CBO_EVENT_EXTRA_REG(0x8136, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x8336, 0xffff, 0x10), + SNBEP_CBO_EVENT_EXTRA_REG(0x4037, 0x40ff, 0x8), + EVENT_EXTRA_END +}; + +static u64 ivt_cbox_filter_mask(int fields) +{ + u64 mask = 0; + + if (fields & 0x1) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_TID; + if (fields & 0x2) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_LINK; + if (fields & 0x4) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_STATE; + if (fields & 0x8) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_NID; + if (fields & 0x10) + mask |= IVT_CB0_MSR_PMON_BOX_FILTER_OPC; + + return mask; +} + +static struct event_constraint * +ivt_cbox_get_constraint(struct intel_uncore_box *box, struct perf_event *event) +{ + return __snbep_cbox_get_constraint(box, event, ivt_cbox_filter_mask); +} + +static int ivt_cbox_hw_config(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event_extra *reg1 = &event->hw.extra_reg; + struct extra_reg *er; + int idx = 0; + + for (er = ivt_uncore_cbox_extra_regs; er->msr; er++) { + if (er->event != (event->hw.config & er->config_mask)) + continue; + idx |= er->idx; + } + + if (idx) { + reg1->reg = SNBEP_C0_MSR_PMON_BOX_FILTER + + SNBEP_CBO_MSR_OFFSET * box->pmu->pmu_idx; + reg1->config = event->attr.config1 & ivt_cbox_filter_mask(idx); + reg1->idx = idx; + } + return 0; +} + +static void ivt_cbox_enable_event(struct intel_uncore_box *box, struct perf_event *event) +{ + struct hw_perf_event *hwc = &event->hw; + struct hw_perf_event_extra *reg1 = &hwc->extra_reg; + + if (reg1->idx != EXTRA_REG_NONE) { + u64 filter = uncore_shared_reg_config(box, 0); + wrmsrl(reg1->reg, filter & 0xffffffff); + wrmsrl(reg1->reg + 6, filter >> 32); + } + + wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN); +} + +static struct intel_uncore_ops ivt_uncore_cbox_ops = { + .init_box = ivt_uncore_msr_init_box, + .disable_box = snbep_uncore_msr_disable_box, + .enable_box = snbep_uncore_msr_enable_box, + .disable_event = snbep_uncore_msr_disable_event, + .enable_event = ivt_cbox_enable_event, + .read_counter = uncore_msr_read_counter, + .hw_config = ivt_cbox_hw_config, + .get_constraint = ivt_cbox_get_constraint, + .put_constraint = snbep_cbox_put_constraint, +}; + +static struct intel_uncore_type ivt_uncore_cbox = { + .name = "cbox", + .num_counters = 4, + .num_boxes = 15, + .perf_ctr_bits = 44, + .event_ctl = SNBEP_C0_MSR_PMON_CTL0, + .perf_ctr = SNBEP_C0_MSR_PMON_CTR0, + .event_mask = IVT_CBO_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_C0_MSR_PMON_BOX_CTL, + .msr_offset = SNBEP_CBO_MSR_OFFSET, + .num_shared_regs = 1, + .constraints = snbep_uncore_cbox_constraints, + .ops = &ivt_uncore_cbox_ops, + .format_group = &ivt_uncore_cbox_format_group, +}; + +static struct intel_uncore_ops ivt_uncore_pcu_ops = { + IVT_UNCORE_MSR_OPS_COMMON_INIT(), + .hw_config = snbep_pcu_hw_config, + .get_constraint = snbep_pcu_get_constraint, + .put_constraint = snbep_pcu_put_constraint, +}; + +static struct intel_uncore_type ivt_uncore_pcu = { + .name = "pcu", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCU_MSR_PMON_CTR0, + .event_ctl = SNBEP_PCU_MSR_PMON_CTL0, + .event_mask = IVT_PCU_MSR_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCU_MSR_PMON_BOX_CTL, + .num_shared_regs = 1, + .ops = &ivt_uncore_pcu_ops, + .format_group = &ivt_uncore_pcu_format_group, +}; + +static struct intel_uncore_type *ivt_msr_uncores[] = { + &ivt_uncore_ubox, + &ivt_uncore_cbox, + &ivt_uncore_pcu, + NULL, +}; + +static struct intel_uncore_type ivt_uncore_ha = { + .name = "ha", + .num_counters = 4, + .num_boxes = 2, + .perf_ctr_bits = 48, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_imc = { + .name = "imc", + .num_counters = 4, + .num_boxes = 8, + .perf_ctr_bits = 48, + .fixed_ctr_bits = 48, + .fixed_ctr = SNBEP_MC_CHy_PCI_PMON_FIXED_CTR, + .fixed_ctl = SNBEP_MC_CHy_PCI_PMON_FIXED_CTL, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_qpi = { + .name = "qpi", + .num_counters = 4, + .num_boxes = 3, + .perf_ctr_bits = 48, + .perf_ctr = SNBEP_PCI_PMON_CTR0, + .event_ctl = SNBEP_PCI_PMON_CTL0, + .event_mask = IVT_QPI_PCI_PMON_RAW_EVENT_MASK, + .box_ctl = SNBEP_PCI_PMON_BOX_CTL, + .ops = &ivt_uncore_pci_ops, + .format_group = &ivt_uncore_qpi_format_group, +}; + +static struct intel_uncore_type ivt_uncore_r2pcie = { + .name = "r2pcie", + .num_counters = 4, + .num_boxes = 1, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r2pcie_constraints, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +static struct intel_uncore_type ivt_uncore_r3qpi = { + .name = "r3qpi", + .num_counters = 3, + .num_boxes = 2, + .perf_ctr_bits = 44, + .constraints = snbep_uncore_r3qpi_constraints, + IVT_UNCORE_PCI_COMMON_INIT(), +}; + +enum { + IVT_PCI_UNCORE_HA, + IVT_PCI_UNCORE_IMC, + IVT_PCI_UNCORE_QPI, + IVT_PCI_UNCORE_R2PCIE, + IVT_PCI_UNCORE_R3QPI, +}; + +static struct intel_uncore_type *ivt_pci_uncores[] = { + [IVT_PCI_UNCORE_HA] = &ivt_uncore_ha, + [IVT_PCI_UNCORE_IMC] = &ivt_uncore_imc, + [IVT_PCI_UNCORE_QPI] = &ivt_uncore_qpi, + [IVT_PCI_UNCORE_R2PCIE] = &ivt_uncore_r2pcie, + [IVT_PCI_UNCORE_R3QPI] = &ivt_uncore_r3qpi, + NULL, +}; + +static DEFINE_PCI_DEVICE_TABLE(ivt_uncore_pci_ids) = { + { /* Home Agent 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe30), + .driver_data = IVT_PCI_UNCORE_HA, + }, + { /* Home Agent 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe38), + .driver_data = IVT_PCI_UNCORE_HA, + }, + { /* MC0 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb4), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb5), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb0), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC0 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xeb1), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef4), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef5), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 3 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef0), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* MC1 Channel 4 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xef1), + .driver_data = IVT_PCI_UNCORE_IMC, + }, + { /* QPI0 Port 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe32), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* QPI0 Port 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe33), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* QPI1 Port 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3a), + .driver_data = IVT_PCI_UNCORE_QPI, + }, + { /* R2PCIe */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe34), + .driver_data = IVT_PCI_UNCORE_R2PCIE, + }, + { /* R3QPI0 Link 0 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe36), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* R3QPI0 Link 1 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe37), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* R3QPI1 Link 2 */ + PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0xe3e), + .driver_data = IVT_PCI_UNCORE_R3QPI, + }, + { /* end: all zeroes */ } +}; + +static struct pci_driver ivt_uncore_pci_driver = { + .name = "ivt_uncore", + .id_table = ivt_uncore_pci_ids, +}; +/* end of IvyTown uncore support */ + /* Sandy Bridge uncore support */ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { @@ -808,9 +1491,6 @@ static struct intel_uncore_type *nhm_msr_uncores[] = { /* end of Nehalem uncore support */ /* Nehalem-EX uncore support */ -#define __BITS_VALUE(x, i, n) ((typeof(x))(((x) >> ((i) * (n))) & \ - ((1ULL << (n)) - 1))) - DEFINE_UNCORE_FORMAT_ATTR(event5, event, "config:1-5"); DEFINE_UNCORE_FORMAT_ATTR(counter, counter, "config:6-7"); DEFINE_UNCORE_FORMAT_ATTR(match, match, "config1:0-63"); @@ -1161,7 +1841,7 @@ static struct extra_reg nhmex_uncore_mbox_extra_regs[] = { }; /* Nehalem-EX or Westmere-EX ? */ -bool uncore_nhmex; +static bool uncore_nhmex; static bool nhmex_mbox_get_shared_reg(struct intel_uncore_box *box, int idx, u64 config) { @@ -1239,7 +1919,7 @@ static void nhmex_mbox_put_shared_reg(struct intel_uncore_box *box, int idx) atomic_sub(1 << (idx * 8), &er->ref); } -u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) +static u64 nhmex_mbox_alter_er(struct perf_event *event, int new_idx, bool modify) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -1554,7 +2234,7 @@ static struct intel_uncore_type nhmex_uncore_mbox = { .format_group = &nhmex_uncore_mbox_format_group, }; -void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) +static void nhmex_rbox_alter_er(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; struct hw_perf_event_extra *reg1 = &hwc->extra_reg; @@ -1724,21 +2404,6 @@ static int nhmex_rbox_hw_config(struct intel_uncore_box *box, struct perf_event return 0; } -static u64 nhmex_rbox_shared_reg_config(struct intel_uncore_box *box, int idx) -{ - struct intel_uncore_extra_reg *er; - unsigned long flags; - u64 config; - - er = &box->shared_regs[idx]; - - raw_spin_lock_irqsave(&er->lock, flags); - config = er->config; - raw_spin_unlock_irqrestore(&er->lock, flags); - - return config; -} - static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event) { struct hw_perf_event *hwc = &event->hw; @@ -1759,7 +2424,7 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per case 2: case 3: wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port), - nhmex_rbox_shared_reg_config(box, 2 + (idx / 6) * 5)); + uncore_shared_reg_config(box, 2 + (idx / 6) * 5)); break; case 4: wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port), @@ -2285,7 +2950,7 @@ out: return ret; } -int uncore_pmu_event_init(struct perf_event *event) +static int uncore_pmu_event_init(struct perf_event *event) { struct intel_uncore_pmu *pmu; struct intel_uncore_box *box; @@ -2428,7 +3093,7 @@ static void __init uncore_types_exit(struct intel_uncore_type **types) static int __init uncore_type_init(struct intel_uncore_type *type) { struct intel_uncore_pmu *pmus; - struct attribute_group *events_group; + struct attribute_group *attr_group; struct attribute **attrs; int i, j; @@ -2438,7 +3103,7 @@ static int __init uncore_type_init(struct intel_uncore_type *type) type->unconstrainted = (struct event_constraint) __EVENT_CONSTRAINT(0, (1ULL << type->num_counters) - 1, - 0, type->num_counters, 0); + 0, type->num_counters, 0, 0); for (i = 0; i < type->num_boxes; i++) { pmus[i].func_id = -1; @@ -2455,19 +3120,19 @@ static int __init uncore_type_init(struct intel_uncore_type *type) while (type->event_descs[i].attr.attr.name) i++; - events_group = kzalloc(sizeof(struct attribute *) * (i + 1) + - sizeof(*events_group), GFP_KERNEL); - if (!events_group) + attr_group = kzalloc(sizeof(struct attribute *) * (i + 1) + + sizeof(*attr_group), GFP_KERNEL); + if (!attr_group) goto fail; - attrs = (struct attribute **)(events_group + 1); - events_group->name = "events"; - events_group->attrs = attrs; + attrs = (struct attribute **)(attr_group + 1); + attr_group->name = "events"; + attr_group->attrs = attrs; for (j = 0; j < i; j++) attrs[j] = &type->event_descs[j].attr.attr; - type->events_group = events_group; + type->events_group = attr_group; } type->pmu_group = &uncore_pmu_attr_group; @@ -2556,6 +3221,8 @@ static void uncore_pci_remove(struct pci_dev *pdev) if (WARN_ON_ONCE(phys_id != box->phys_id)) return; + pci_set_drvdata(pdev, NULL); + raw_spin_lock(&uncore_box_lock); list_del(&box->list); raw_spin_unlock(&uncore_box_lock); @@ -2574,11 +3241,7 @@ static void uncore_pci_remove(struct pci_dev *pdev) static int uncore_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id) { - struct intel_uncore_type *type; - - type = (struct intel_uncore_type *)id->driver_data; - - return uncore_pci_add(type, pdev); + return uncore_pci_add(pci_uncores[id->driver_data], pdev); } static int __init uncore_pci_init(void) @@ -2587,12 +3250,19 @@ static int __init uncore_pci_init(void) switch (boot_cpu_data.x86_model) { case 45: /* Sandy Bridge-EP */ - ret = snbep_pci2phy_map_init(); + ret = snbep_pci2phy_map_init(0x3ce0); if (ret) return ret; pci_uncores = snbep_pci_uncores; uncore_pci_driver = &snbep_uncore_pci_driver; break; + case 62: /* IvyTown */ + ret = snbep_pci2phy_map_init(0x0e1e); + if (ret) + return ret; + pci_uncores = ivt_pci_uncores; + uncore_pci_driver = &ivt_uncore_pci_driver; + break; default: return 0; } @@ -2622,6 +3292,21 @@ static void __init uncore_pci_exit(void) } } +/* CPU hot plug/unplug are serialized by cpu_add_remove_lock mutex */ +static LIST_HEAD(boxes_to_free); + +static void __cpuinit uncore_kfree_boxes(void) +{ + struct intel_uncore_box *box; + + while (!list_empty(&boxes_to_free)) { + box = list_entry(boxes_to_free.next, + struct intel_uncore_box, list); + list_del(&box->list); + kfree(box); + } +} + static void __cpuinit uncore_cpu_dying(int cpu) { struct intel_uncore_type *type; @@ -2636,7 +3321,7 @@ static void __cpuinit uncore_cpu_dying(int cpu) box = *per_cpu_ptr(pmu->box, cpu); *per_cpu_ptr(pmu->box, cpu) = NULL; if (box && atomic_dec_and_test(&box->refcnt)) - kfree(box); + list_add(&box->list, &boxes_to_free); } } } @@ -2666,8 +3351,11 @@ static int __cpuinit uncore_cpu_starting(int cpu) if (exist && exist->phys_id == phys_id) { atomic_inc(&exist->refcnt); *per_cpu_ptr(pmu->box, cpu) = exist; - kfree(box); - box = NULL; + if (box) { + list_add(&box->list, + &boxes_to_free); + box = NULL; + } break; } } @@ -2806,6 +3494,10 @@ static int case CPU_DYING: uncore_cpu_dying(cpu); break; + case CPU_ONLINE: + case CPU_DEAD: + uncore_kfree_boxes(); + break; default: break; } @@ -2853,11 +3545,12 @@ static int __init uncore_cpu_init(void) msr_uncores = nhm_msr_uncores; break; case 42: /* Sandy Bridge */ + case 58: /* Ivy Bridge */ if (snb_uncore_cbox.num_boxes > max_cores) snb_uncore_cbox.num_boxes = max_cores; msr_uncores = snb_msr_uncores; break; - case 45: /* Sandy Birdge-EP */ + case 45: /* Sandy Bridge-EP */ if (snbep_uncore_cbox.num_boxes > max_cores) snbep_uncore_cbox.num_boxes = max_cores; msr_uncores = snbep_msr_uncores; @@ -2871,6 +3564,12 @@ static int __init uncore_cpu_init(void) nhmex_uncore_cbox.num_boxes = max_cores; msr_uncores = nhmex_msr_uncores; break; + case 62: /* IvyTown */ + if (ivt_uncore_cbox.num_boxes > max_cores) + ivt_uncore_cbox.num_boxes = max_cores; + msr_uncores = ivt_msr_uncores; + break; + default: return 0; } diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.h b/arch/x86/kernel/cpu/perf_event_intel_uncore.h index e68a4550e95..f9528917f6e 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_uncore.h +++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.h @@ -76,7 +76,7 @@ #define SNBEP_PMON_CTL_UMASK_MASK 0x0000ff00 #define SNBEP_PMON_CTL_RST (1 << 17) #define SNBEP_PMON_CTL_EDGE_DET (1 << 18) -#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) /* only for QPI */ +#define SNBEP_PMON_CTL_EV_SEL_EXT (1 << 21) #define SNBEP_PMON_CTL_EN (1 << 22) #define SNBEP_PMON_CTL_INVERT (1 << 23) #define SNBEP_PMON_CTL_TRESH_MASK 0xff000000 @@ -148,9 +148,20 @@ #define SNBEP_C0_MSR_PMON_CTL0 0xd10 #define SNBEP_C0_MSR_PMON_BOX_CTL 0xd04 #define SNBEP_C0_MSR_PMON_BOX_FILTER 0xd14 -#define SNBEP_CB0_MSR_PMON_BOX_FILTER_MASK 0xfffffc1f #define SNBEP_CBO_MSR_OFFSET 0x20 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_TID 0x1f +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_NID 0x3fc00 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_STATE 0x7c0000 +#define SNBEP_CB0_MSR_PMON_BOX_FILTER_OPC 0xff800000 + +#define SNBEP_CBO_EVENT_EXTRA_REG(e, m, i) { \ + .event = (e), \ + .msr = SNBEP_C0_MSR_PMON_BOX_FILTER, \ + .config_mask = (m), \ + .idx = (i) \ +} + /* SNB-EP PCU register */ #define SNBEP_PCU_MSR_PMON_CTR0 0xc36 #define SNBEP_PCU_MSR_PMON_CTL0 0xc30 @@ -160,6 +171,55 @@ #define SNBEP_PCU_MSR_CORE_C3_CTR 0x3fc #define SNBEP_PCU_MSR_CORE_C6_CTR 0x3fd +/* IVT event control */ +#define IVT_PMON_BOX_CTL_INT (SNBEP_PMON_BOX_CTL_RST_CTRL | \ + SNBEP_PMON_BOX_CTL_RST_CTRS) +#define IVT_PMON_RAW_EVENT_MASK (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PMON_CTL_TRESH_MASK) +/* IVT Ubox */ +#define IVT_U_MSR_PMON_GLOBAL_CTL 0xc00 +#define IVT_U_PMON_GLOBAL_FRZ_ALL (1 << 31) +#define IVT_U_PMON_GLOBAL_UNFRZ_ALL (1 << 29) + +#define IVT_U_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_UMASK_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_U_MSR_PMON_CTL_TRESH_MASK) +/* IVT Cbo */ +#define IVT_CBO_MSR_PMON_RAW_EVENT_MASK (IVT_PMON_RAW_EVENT_MASK | \ + SNBEP_CBO_PMON_CTL_TID_EN) + +#define IVT_CB0_MSR_PMON_BOX_FILTER_TID (0x1fULL << 0) +#define IVT_CB0_MSR_PMON_BOX_FILTER_LINK (0xfULL << 5) +#define IVT_CB0_MSR_PMON_BOX_FILTER_STATE (0x3fULL << 17) +#define IVT_CB0_MSR_PMON_BOX_FILTER_NID (0xffffULL << 32) +#define IVT_CB0_MSR_PMON_BOX_FILTER_OPC (0x1ffULL << 52) +#define IVT_CB0_MSR_PMON_BOX_FILTER_C6 (0x1ULL << 61) +#define IVT_CB0_MSR_PMON_BOX_FILTER_NC (0x1ULL << 62) +#define IVT_CB0_MSR_PMON_BOX_FILTER_IOSC (0x1ULL << 63) + +/* IVT home agent */ +#define IVT_HA_PCI_PMON_CTL_Q_OCC_RST (1 << 16) +#define IVT_HA_PCI_PMON_RAW_EVENT_MASK \ + (IVT_PMON_RAW_EVENT_MASK | \ + IVT_HA_PCI_PMON_CTL_Q_OCC_RST) +/* IVT PCU */ +#define IVT_PCU_MSR_PMON_RAW_EVENT_MASK \ + (SNBEP_PMON_CTL_EV_SEL_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_SEL_MASK | \ + SNBEP_PMON_CTL_EDGE_DET | \ + SNBEP_PCU_MSR_PMON_CTL_TRESH_MASK | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_INVERT | \ + SNBEP_PCU_MSR_PMON_CTL_OCC_EDGE_DET) +/* IVT QPI */ +#define IVT_QPI_PCI_PMON_RAW_EVENT_MASK \ + (IVT_PMON_RAW_EVENT_MASK | \ + SNBEP_PMON_CTL_EV_SEL_EXT) + /* NHM-EX event control */ #define NHMEX_PMON_CTL_EV_SEL_MASK 0x000000ff #define NHMEX_PMON_CTL_UMASK_MASK 0x0000ff00 diff --git a/arch/x86/kernel/cpu/perf_event_knc.c b/arch/x86/kernel/cpu/perf_event_knc.c index 4b7731bf23a..838fa8772c6 100644 --- a/arch/x86/kernel/cpu/perf_event_knc.c +++ b/arch/x86/kernel/cpu/perf_event_knc.c @@ -17,7 +17,7 @@ static const u64 knc_perfmon_event_map[] = [PERF_COUNT_HW_BRANCH_MISSES] = 0x002b, }; -static __initconst u64 knc_hw_cache_event_ids +static const u64 __initconst knc_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = @@ -284,7 +284,7 @@ static struct attribute *intel_knc_formats_attr[] = { NULL, }; -static __initconst struct x86_pmu knc_pmu = { +static const struct x86_pmu knc_pmu __initconst = { .name = "knc", .handle_irq = knc_pmu_handle_irq, .disable_all = knc_pmu_disable_all, diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c index 92c7e39a079..3486e666035 100644 --- a/arch/x86/kernel/cpu/perf_event_p4.c +++ b/arch/x86/kernel/cpu/perf_event_p4.c @@ -895,8 +895,8 @@ static void p4_pmu_disable_pebs(void) * So at moment let leave metrics turned on forever -- it's * ok for now but need to be revisited! * - * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)0); - * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)0); + * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0); + * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0); */ } @@ -910,8 +910,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event) * asserted again and again */ (void)wrmsrl_safe(hwc->config_base, - (u64)(p4_config_unpack_cccr(hwc->config)) & - ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); + p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED); } static void p4_pmu_disable_all(void) @@ -957,7 +956,7 @@ static void p4_pmu_enable_event(struct perf_event *event) u64 escr_addr, cccr; bind = &p4_event_bind_map[idx]; - escr_addr = (u64)bind->escr_msr[thread]; + escr_addr = bind->escr_msr[thread]; /* * - we dont support cascaded counters yet diff --git a/arch/x86/kernel/cpu/perf_event_p6.c b/arch/x86/kernel/cpu/perf_event_p6.c index 4820c232a0b..b1e2fe11532 100644 --- a/arch/x86/kernel/cpu/perf_event_p6.c +++ b/arch/x86/kernel/cpu/perf_event_p6.c @@ -19,7 +19,7 @@ static const u64 p6_perfmon_event_map[] = }; -static u64 p6_hw_cache_event_ids +static const u64 __initconst p6_hw_cache_event_ids [PERF_COUNT_HW_CACHE_MAX] [PERF_COUNT_HW_CACHE_OP_MAX] [PERF_COUNT_HW_CACHE_RESULT_MAX] = diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c index e280253f6f9..37a198bd48c 100644 --- a/arch/x86/kernel/cpu/proc.c +++ b/arch/x86/kernel/cpu/proc.c @@ -34,9 +34,9 @@ static void show_cpuinfo_misc(struct seq_file *m, struct cpuinfo_x86 *c) "fpu_exception\t: %s\n" "cpuid level\t: %d\n" "wp\t\t: %s\n", - c->fdiv_bug ? "yes" : "no", - c->f00f_bug ? "yes" : "no", - c->coma_bug ? "yes" : "no", + static_cpu_has_bug(X86_BUG_FDIV) ? "yes" : "no", + static_cpu_has_bug(X86_BUG_F00F) ? "yes" : "no", + static_cpu_has_bug(X86_BUG_COMA) ? "yes" : "no", c->hard_math ? "yes" : "no", c->hard_math ? "yes" : "no", c->cpuid_level, diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index ee8e9abc859..d92b5dad15d 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -39,8 +39,9 @@ void __cpuinit init_scattered_cpuid_features(struct cpuinfo_x86 *c) { X86_FEATURE_APERFMPERF, CR_ECX, 0, 0x00000006, 0 }, { X86_FEATURE_EPB, CR_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_XSAVEOPT, CR_EAX, 0, 0x0000000d, 1 }, - { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, { X86_FEATURE_HW_PSTATE, CR_EDX, 7, 0x80000007, 0 }, + { X86_FEATURE_CPB, CR_EDX, 9, 0x80000007, 0 }, + { X86_FEATURE_PROC_FEEDBACK, CR_EDX,11, 0x80000007, 0 }, { X86_FEATURE_NPT, CR_EDX, 0, 0x8000000a, 0 }, { X86_FEATURE_LBRV, CR_EDX, 1, 0x8000000a, 0 }, { X86_FEATURE_SVML, CR_EDX, 2, 0x8000000a, 0 }, diff --git a/arch/x86/kernel/doublefault_32.c b/arch/x86/kernel/doublefault_32.c index 37250fe490b..155a13f33ed 100644 --- a/arch/x86/kernel/doublefault_32.c +++ b/arch/x86/kernel/doublefault_32.c @@ -20,7 +20,7 @@ static void doublefault_fn(void) struct desc_ptr gdt_desc = {0, 0}; unsigned long gdt, tss; - store_gdt(&gdt_desc); + native_store_gdt(&gdt_desc); gdt = gdt_desc.address; printk(KERN_EMERG "PANIC: double fault, gdt at %08lx [%d bytes]\n", gdt, gdt_desc.size); diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c index c8797d55b24..deb6421c9e6 100644 --- a/arch/x86/kernel/dumpstack.c +++ b/arch/x86/kernel/dumpstack.c @@ -176,26 +176,20 @@ void show_trace(struct task_struct *task, struct pt_regs *regs, void show_stack(struct task_struct *task, unsigned long *sp) { - show_stack_log_lvl(task, NULL, sp, 0, ""); -} - -/* - * The architecture-independent dump_stack generator - */ -void dump_stack(void) -{ - unsigned long bp; + unsigned long bp = 0; unsigned long stack; - bp = stack_frame(current, NULL); - printk("Pid: %d, comm: %.20s %s %s %.*s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version); - show_trace(NULL, NULL, &stack, bp); + /* + * Stack frames below this one aren't interesting. Don't show them + * if we're printing for %current. + */ + if (!sp && (!task || task == current)) { + sp = &stack; + bp = stack_frame(current, NULL); + } + + show_stack_log_lvl(task, NULL, sp, bp, ""); } -EXPORT_SYMBOL(dump_stack); static arch_spinlock_t die_lock = __ARCH_SPIN_LOCK_UNLOCKED; static int die_owner = -1; diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c index 1038a417ea5..f2a1770ca17 100644 --- a/arch/x86/kernel/dumpstack_32.c +++ b/arch/x86/kernel/dumpstack_32.c @@ -86,11 +86,9 @@ void show_regs(struct pt_regs *regs) { int i; + show_regs_print_info(KERN_EMERG); __show_regs(regs, !user_mode_vm(regs)); - pr_emerg("Process %.*s (pid: %d, ti=%p task=%p task.ti=%p)\n", - TASK_COMM_LEN, current->comm, task_pid_nr(current), - current_thread_info(), current, task_thread_info(current)); /* * When in-kernel, we also print out the stack and code at the * time of the fault.. diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c index b653675d528..addb207dab9 100644 --- a/arch/x86/kernel/dumpstack_64.c +++ b/arch/x86/kernel/dumpstack_64.c @@ -249,14 +249,10 @@ void show_regs(struct pt_regs *regs) { int i; unsigned long sp; - const int cpu = smp_processor_id(); - struct task_struct *cur = current; sp = regs->sp; - printk("CPU %d ", cpu); + show_regs_print_info(KERN_DEFAULT); __show_regs(regs, 1); - printk(KERN_DEFAULT "Process %s (pid: %d, threadinfo %p, task %p)\n", - cur->comm, cur->pid, task_thread_info(cur), cur); /* * When in-kernel, we also print out the stack and code at the diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c index 9b9f18b4991..d15f575a861 100644 --- a/arch/x86/kernel/early_printk.c +++ b/arch/x86/kernel/early_printk.c @@ -169,25 +169,9 @@ static struct console early_serial_console = { .index = -1, }; -/* Direct interface for emergencies */ -static struct console *early_console = &early_vga_console; -static int __initdata early_console_initialized; - -asmlinkage void early_printk(const char *fmt, ...) -{ - char buf[512]; - int n; - va_list ap; - - va_start(ap, fmt); - n = vscnprintf(buf, sizeof(buf), fmt, ap); - early_console->write(early_console, buf, n); - va_end(ap); -} - static inline void early_console_register(struct console *con, int keep_early) { - if (early_console->index != -1) { + if (con->index != -1) { printk(KERN_CRIT "ERROR: earlyprintk= %s already used\n", con->name); return; @@ -207,9 +191,8 @@ static int __init setup_early_printk(char *buf) if (!buf) return 0; - if (early_console_initialized) + if (early_console) return 0; - early_console_initialized = 1; keep = (strstr(buf, "keep") != NULL); diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index c5e403f6d86..dab95a85f7f 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -34,6 +34,7 @@ extern pgd_t early_level4_pgt[PTRS_PER_PGD]; extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD]; static unsigned int __initdata next_early_pgt = 2; +pmdval_t __initdata early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX); /* Wipe all early page tables except for the kernel symbol map */ static void __init reset_early_page_tables(void) @@ -99,7 +100,7 @@ again: pmd_p[i] = 0; *pud_p = (pudval_t)pmd_p - __START_KERNEL_map + phys_base + _KERNPG_TABLE; } - pmd = (physaddr & PMD_MASK) + (__PAGE_KERNEL_LARGE & ~_PAGE_GLOBAL); + pmd = (physaddr & PMD_MASK) + early_pmd_flags; pmd_p[pmd_index(address)] = pmd; return 0; @@ -144,10 +145,10 @@ void __init x86_64_start_kernel(char * real_mode_data) * Build-time sanity checks on the kernel image and module * area mappings. (these are purely build-time and produce no code) */ - BUILD_BUG_ON(MODULES_VADDR < KERNEL_IMAGE_START); - BUILD_BUG_ON(MODULES_VADDR-KERNEL_IMAGE_START < KERNEL_IMAGE_SIZE); + BUILD_BUG_ON(MODULES_VADDR < __START_KERNEL_map); + BUILD_BUG_ON(MODULES_VADDR - __START_KERNEL_map < KERNEL_IMAGE_SIZE); BUILD_BUG_ON(MODULES_LEN + KERNEL_IMAGE_SIZE > 2*PUD_SIZE); - BUILD_BUG_ON((KERNEL_IMAGE_START & ~PMD_MASK) != 0); + BUILD_BUG_ON((__START_KERNEL_map & ~PMD_MASK) != 0); BUILD_BUG_ON((MODULES_VADDR & ~PMD_MASK) != 0); BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL)); BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S index 6859e962644..08f7e803909 100644 --- a/arch/x86/kernel/head_64.S +++ b/arch/x86/kernel/head_64.S @@ -200,6 +200,7 @@ ENTRY(secondary_startup_64) btl $20,%edi /* No Execute supported? */ jnc 1f btsl $_EFER_NX, %eax + btsq $_PAGE_BIT_NX,early_pmd_flags(%rip) 1: wrmsr /* Make changes effective */ /* Setup cr0 */ diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c index 6ae6ea1d27d..ac0631d8996 100644 --- a/arch/x86/kernel/irq.c +++ b/arch/x86/kernel/irq.c @@ -165,10 +165,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu) u64 arch_irq_stat(void) { u64 sum = atomic_read(&irq_err_count); - -#ifdef CONFIG_X86_IO_APIC - sum += atomic_read(&irq_mis_count); -#endif return sum; } diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c index 3f06e614998..9895a9a4138 100644 --- a/arch/x86/kernel/kprobes/core.c +++ b/arch/x86/kernel/kprobes/core.c @@ -353,7 +353,11 @@ int __kprobes __copy_instruction(u8 *dest, u8 *src) * have given. */ newdisp = (u8 *) src + (s64) insn.displacement.value - (u8 *) dest; - BUG_ON((s64) (s32) newdisp != newdisp); /* Sanity check. */ + if ((s64) (s32) newdisp != newdisp) { + pr_err("Kprobes error: new displacement does not fit into s32 (%llx)\n", newdisp); + pr_err("\tSrc: %p, Dest: %p, old disp: %x\n", src, dest, insn.displacement.value); + return 0; + } disp = (u8 *) dest + insn_offset_displacement(&insn); *(s32 *) disp = (s32) newdisp; } @@ -375,6 +379,9 @@ static void __kprobes arch_copy_kprobe(struct kprobe *p) else p->ainsn.boostable = -1; + /* Check whether the instruction modifies Interrupt Flag or not */ + p->ainsn.if_modifier = is_IF_modifier(p->ainsn.insn); + /* Also, displacement change doesn't affect the first byte */ p->opcode = p->ainsn.insn[0]; } @@ -434,7 +441,7 @@ static void __kprobes set_current_kprobe(struct kprobe *p, struct pt_regs *regs, __this_cpu_write(current_kprobe, p); kcb->kprobe_saved_flags = kcb->kprobe_old_flags = (regs->flags & (X86_EFLAGS_TF | X86_EFLAGS_IF)); - if (is_IF_modifier(p->ainsn.insn)) + if (p->ainsn.if_modifier) kcb->kprobe_saved_flags &= ~X86_EFLAGS_IF; } diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index b686a904d7c..cd6d9a5a42f 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -20,6 +20,7 @@ * Authors: Anthony Liguori <aliguori@us.ibm.com> */ +#include <linux/context_tracking.h> #include <linux/module.h> #include <linux/kernel.h> #include <linux/kvm_para.h> @@ -43,7 +44,6 @@ #include <asm/apicdef.h> #include <asm/hypervisor.h> #include <asm/kvm_guest.h> -#include <asm/context_tracking.h> static int kvmapf = 1; @@ -254,16 +254,18 @@ EXPORT_SYMBOL_GPL(kvm_read_and_reset_pf_reason); dotraplinkage void __kprobes do_async_page_fault(struct pt_regs *regs, unsigned long error_code) { + enum ctx_state prev_state; + switch (kvm_read_and_reset_pf_reason()) { default: do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ - exception_enter(regs); + prev_state = exception_enter(); exit_idle(); kvm_async_pf_task_wait((u32)read_cr2()); - exception_exit(regs); + exception_exit(prev_state); break; case KVM_PV_REASON_PAGE_READY: rcu_irq_enter(); diff --git a/arch/x86/kernel/microcode_core_early.c b/arch/x86/kernel/microcode_core_early.c index 577db8417d1..833d51d6ee0 100644 --- a/arch/x86/kernel/microcode_core_early.c +++ b/arch/x86/kernel/microcode_core_early.c @@ -45,9 +45,6 @@ static int __cpuinit x86_vendor(void) u32 eax = 0x00000000; u32 ebx, ecx = 0, edx; - if (!have_cpuid_p()) - return X86_VENDOR_UNKNOWN; - native_cpuid(&eax, &ebx, &ecx, &edx); if (CPUID_IS(CPUID_INTEL1, CPUID_INTEL2, CPUID_INTEL3, ebx, ecx, edx)) @@ -59,18 +56,45 @@ static int __cpuinit x86_vendor(void) return X86_VENDOR_UNKNOWN; } +static int __cpuinit x86_family(void) +{ + u32 eax = 0x00000001; + u32 ebx, ecx = 0, edx; + int x86; + + native_cpuid(&eax, &ebx, &ecx, &edx); + + x86 = (eax >> 8) & 0xf; + if (x86 == 15) + x86 += (eax >> 20) & 0xff; + + return x86; +} + void __init load_ucode_bsp(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; - if (vendor == X86_VENDOR_INTEL) + vendor = x86_vendor(); + x86 = x86_family(); + + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_bsp(); } void __cpuinit load_ucode_ap(void) { - int vendor = x86_vendor(); + int vendor, x86; + + if (!have_cpuid_p()) + return; + + vendor = x86_vendor(); + x86 = x86_family(); - if (vendor == X86_VENDOR_INTEL) + if (vendor == X86_VENDOR_INTEL && x86 >= 6) load_ucode_intel_ap(); } diff --git a/arch/x86/kernel/microcode_intel_early.c b/arch/x86/kernel/microcode_intel_early.c index 7890bc83895..d893e8ed8ac 100644 --- a/arch/x86/kernel/microcode_intel_early.c +++ b/arch/x86/kernel/microcode_intel_early.c @@ -90,13 +90,13 @@ microcode_phys(struct microcode_intel **mc_saved_tmp, struct microcode_intel ***mc_saved; mc_saved = (struct microcode_intel ***) - __pa_symbol(&mc_saved_data->mc_saved); + __pa_nodebug(&mc_saved_data->mc_saved); for (i = 0; i < mc_saved_data->mc_saved_count; i++) { struct microcode_intel *p; p = *(struct microcode_intel **) - __pa(mc_saved_data->mc_saved + i); - mc_saved_tmp[i] = (struct microcode_intel *)__pa(p); + __pa_nodebug(mc_saved_data->mc_saved + i); + mc_saved_tmp[i] = (struct microcode_intel *)__pa_nodebug(p); } } #endif @@ -562,7 +562,7 @@ scan_microcode(unsigned long start, unsigned long end, struct cpio_data cd; long offset = 0; #ifdef CONFIG_X86_32 - char *p = (char *)__pa_symbol(ucode_name); + char *p = (char *)__pa_nodebug(ucode_name); #else char *p = ucode_name; #endif @@ -630,8 +630,8 @@ static void __cpuinit print_ucode(struct ucode_cpu_info *uci) if (mc_intel == NULL) return; - delay_ucode_info_p = (int *)__pa_symbol(&delay_ucode_info); - current_mc_date_p = (int *)__pa_symbol(¤t_mc_date); + delay_ucode_info_p = (int *)__pa_nodebug(&delay_ucode_info); + current_mc_date_p = (int *)__pa_nodebug(¤t_mc_date); *delay_ucode_info_p = 1; *current_mc_date_p = mc_intel->hdr.date; @@ -659,8 +659,8 @@ static inline void __cpuinit print_ucode(struct ucode_cpu_info *uci) } #endif -static int apply_microcode_early(struct mc_saved_data *mc_saved_data, - struct ucode_cpu_info *uci) +static int __cpuinit apply_microcode_early(struct mc_saved_data *mc_saved_data, + struct ucode_cpu_info *uci) { struct microcode_intel *mc_intel; unsigned int val[2]; @@ -741,15 +741,15 @@ load_ucode_intel_bsp(void) #ifdef CONFIG_X86_32 struct boot_params *boot_params_p; - boot_params_p = (struct boot_params *)__pa_symbol(&boot_params); + boot_params_p = (struct boot_params *)__pa_nodebug(&boot_params); ramdisk_image = boot_params_p->hdr.ramdisk_image; ramdisk_size = boot_params_p->hdr.ramdisk_size; initrd_start_early = ramdisk_image; initrd_end_early = initrd_start_early + ramdisk_size; _load_ucode_intel_bsp( - (struct mc_saved_data *)__pa_symbol(&mc_saved_data), - (unsigned long *)__pa_symbol(&mc_saved_in_initrd), + (struct mc_saved_data *)__pa_nodebug(&mc_saved_data), + (unsigned long *)__pa_nodebug(&mc_saved_in_initrd), initrd_start_early, initrd_end_early, &uci); #else ramdisk_image = boot_params.hdr.ramdisk_image; @@ -772,10 +772,10 @@ void __cpuinit load_ucode_intel_ap(void) unsigned long *initrd_start_p; mc_saved_in_initrd_p = - (unsigned long *)__pa_symbol(mc_saved_in_initrd); - mc_saved_data_p = (struct mc_saved_data *)__pa_symbol(&mc_saved_data); - initrd_start_p = (unsigned long *)__pa_symbol(&initrd_start); - initrd_start_addr = (unsigned long)__pa_symbol(*initrd_start_p); + (unsigned long *)__pa_nodebug(mc_saved_in_initrd); + mc_saved_data_p = (struct mc_saved_data *)__pa_nodebug(&mc_saved_data); + initrd_start_p = (unsigned long *)__pa_nodebug(&initrd_start); + initrd_start_addr = (unsigned long)__pa_nodebug(*initrd_start_p); #else mc_saved_data_p = &mc_saved_data; mc_saved_in_initrd_p = mc_saved_in_initrd; diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c index 17fff18a103..cd6de64cc48 100644 --- a/arch/x86/kernel/paravirt.c +++ b/arch/x86/kernel/paravirt.c @@ -263,6 +263,18 @@ void paravirt_leave_lazy_mmu(void) leave_lazy(PARAVIRT_LAZY_MMU); } +void paravirt_flush_lazy_mmu(void) +{ + preempt_disable(); + + if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { + arch_leave_lazy_mmu_mode(); + arch_enter_lazy_mmu_mode(); + } + + preempt_enable(); +} + void paravirt_start_context_switch(struct task_struct *prev) { BUG_ON(preemptible()); @@ -292,18 +304,6 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void) return this_cpu_read(paravirt_lazy_mode); } -void arch_flush_lazy_mmu_mode(void) -{ - preempt_disable(); - - if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) { - arch_leave_lazy_mmu_mode(); - arch_enter_lazy_mmu_mode(); - } - - preempt_enable(); -} - struct pv_info pv_info = { .name = "bare hardware", .paravirt_enabled = 0, @@ -360,7 +360,6 @@ struct pv_cpu_ops pv_cpu_ops = { .set_ldt = native_set_ldt, .load_gdt = native_load_gdt, .load_idt = native_load_idt, - .store_gdt = native_store_gdt, .store_idt = native_store_idt, .store_tr = native_store_tr, .load_tls = native_load_tls, @@ -475,6 +474,7 @@ struct pv_mmu_ops pv_mmu_ops = { .lazy_mode = { .enter = paravirt_nop, .leave = paravirt_nop, + .flush = paravirt_nop, }, .set_fixmap = native_set_fixmap, diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index 14ae10031ff..607af0d4d5e 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -121,30 +121,6 @@ void exit_thread(void) drop_fpu(me); } -void show_regs_common(void) -{ - const char *vendor, *product, *board; - - vendor = dmi_get_system_info(DMI_SYS_VENDOR); - if (!vendor) - vendor = ""; - product = dmi_get_system_info(DMI_PRODUCT_NAME); - if (!product) - product = ""; - - /* Board Name is optional */ - board = dmi_get_system_info(DMI_BOARD_NAME); - - printk(KERN_DEFAULT "Pid: %d, comm: %.20s %s %s %.*s %s %s%s%s\n", - current->pid, current->comm, print_tainted(), - init_utsname()->release, - (int)strcspn(init_utsname()->version, " "), - init_utsname()->version, - vendor, product, - board ? "/" : "", - board ? board : ""); -} - void flush_thread(void) { struct task_struct *tsk = current; @@ -301,13 +277,7 @@ void exit_idle(void) } #endif -/* - * The idle thread. There's no useful work to be - * done, so just try to conserve power and have a - * low exit latency (ie sit in a loop waiting for - * somebody to say that they'd like to reschedule) - */ -void cpu_idle(void) +void arch_cpu_idle_prepare(void) { /* * If we're the non-boot CPU, nothing set the stack canary up @@ -317,71 +287,40 @@ void cpu_idle(void) * canaries already on the stack wont ever trigger). */ boot_init_stack_canary(); - current_thread_info()->status |= TS_POLLING; - - while (1) { - tick_nohz_idle_enter(); - - while (!need_resched()) { - rmb(); - - if (cpu_is_offline(smp_processor_id())) - play_dead(); - - /* - * Idle routines should keep interrupts disabled - * from here on, until they go to idle. - * Otherwise, idle callbacks can misfire. - */ - local_touch_nmi(); - local_irq_disable(); - - enter_idle(); - - /* Don't trace irqs off for idle */ - stop_critical_timings(); - - /* enter_idle() needs rcu for notifiers */ - rcu_idle_enter(); +} - if (cpuidle_idle_call()) - x86_idle(); +void arch_cpu_idle_enter(void) +{ + local_touch_nmi(); + enter_idle(); +} - rcu_idle_exit(); - start_critical_timings(); +void arch_cpu_idle_exit(void) +{ + __exit_idle(); +} - /* In many cases the interrupt that ended idle - has already called exit_idle. But some idle - loops can be woken up without interrupt. */ - __exit_idle(); - } +void arch_cpu_idle_dead(void) +{ + play_dead(); +} - tick_nohz_idle_exit(); - preempt_enable_no_resched(); - schedule(); - preempt_disable(); - } +/* + * Called from the generic idle code. + */ +void arch_cpu_idle(void) +{ + if (cpuidle_idle_call()) + x86_idle(); } /* - * We use this if we don't have any better - * idle routine.. + * We use this if we don't have any better idle routine.. */ void default_idle(void) { trace_cpu_idle_rcuidle(1, smp_processor_id()); - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - - if (!need_resched()) - safe_halt(); /* enables interrupts racelessly */ - else - local_irq_enable(); - current_thread_info()->status |= TS_POLLING; + safe_halt(); trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); } #ifdef CONFIG_APM_MODULE @@ -411,20 +350,6 @@ void stop_this_cpu(void *dummy) halt(); } -/* - * On SMP it's slightly faster (but much more power-consuming!) - * to poll the ->work.need_resched flag instead of waiting for the - * cross-CPU IPI to arrive. Use this option with caution. - */ -static void poll_idle(void) -{ - trace_cpu_idle_rcuidle(0, smp_processor_id()); - local_irq_enable(); - while (!need_resched()) - cpu_relax(); - trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id()); -} - bool amd_e400_c1e_detected; EXPORT_SYMBOL(amd_e400_c1e_detected); @@ -489,13 +414,13 @@ static void amd_e400_idle(void) void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c) { #ifdef CONFIG_SMP - if (x86_idle == poll_idle && smp_num_siblings > 1) + if (boot_option_idle_override == IDLE_POLL && smp_num_siblings > 1) pr_warn_once("WARNING: polling idle and HT enabled, performance may degrade\n"); #endif - if (x86_idle) + if (x86_idle || boot_option_idle_override == IDLE_POLL) return; - if (cpu_has_amd_erratum(amd_erratum_400)) { + if (cpu_has_bug(c, X86_BUG_AMD_APIC_C1E)) { /* E400: APIC timer interrupt does not wake up CPU from C1e */ pr_info("using AMD E400 aware idle routine\n"); x86_idle = amd_e400_idle; @@ -517,8 +442,8 @@ static int __init idle_setup(char *str) if (!strcmp(str, "poll")) { pr_info("using polling idle threads\n"); - x86_idle = poll_idle; boot_option_idle_override = IDLE_POLL; + cpu_idle_poll_ctrl(true); } else if (!strcmp(str, "halt")) { /* * When the boot option of idle=halt is added, halt is diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c index b5a8905785e..7305f7dfc7a 100644 --- a/arch/x86/kernel/process_32.c +++ b/arch/x86/kernel/process_32.c @@ -84,8 +84,6 @@ void __show_regs(struct pt_regs *regs, int all) savesegment(gs, gs); } - show_regs_common(); - printk(KERN_DEFAULT "EIP: %04x:[<%08lx>] EFLAGS: %08lx CPU: %d\n", (u16)regs->cs, regs->ip, regs->flags, smp_processor_id()); diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 0f49677da51..355ae06dbf9 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -62,7 +62,6 @@ void __show_regs(struct pt_regs *regs, int all) unsigned int fsindex, gsindex; unsigned int ds, cs, es; - show_regs_common(); printk(KERN_DEFAULT "RIP: %04lx:[<%016lx>] ", regs->cs & 0xffff, regs->ip); printk_address(regs->ip, 1); printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx\n", regs->ss, diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c index 26ee48a33dc..04ee1e2e4c0 100644 --- a/arch/x86/kernel/quirks.c +++ b/arch/x86/kernel/quirks.c @@ -354,18 +354,22 @@ static void ati_force_hpet_resume(void) static u32 ati_ixp4x0_rev(struct pci_dev *dev) { - u32 d; - u8 b; + int err = 0; + u32 d = 0; + u8 b = 0; - pci_read_config_byte(dev, 0xac, &b); + err = pci_read_config_byte(dev, 0xac, &b); b &= ~(1<<5); - pci_write_config_byte(dev, 0xac, b); - pci_read_config_dword(dev, 0x70, &d); + err |= pci_write_config_byte(dev, 0xac, b); + err |= pci_read_config_dword(dev, 0x70, &d); d |= 1<<8; - pci_write_config_dword(dev, 0x70, d); - pci_read_config_dword(dev, 0x8, &d); + err |= pci_write_config_dword(dev, 0x70, d); + err |= pci_read_config_dword(dev, 0x8, &d); d &= 0xff; dev_printk(KERN_DEBUG, &dev->dev, "SB4X0 revision 0x%x\n", d); + + WARN_ON_ONCE(err); + return d; } diff --git a/arch/x86/kernel/rtc.c b/arch/x86/kernel/rtc.c index 2e8f3d3b564..198eb201ed3 100644 --- a/arch/x86/kernel/rtc.c +++ b/arch/x86/kernel/rtc.c @@ -13,6 +13,7 @@ #include <asm/x86_init.h> #include <asm/time.h> #include <asm/mrst.h> +#include <asm/rtc.h> #ifdef CONFIG_X86_32 /* @@ -36,70 +37,24 @@ EXPORT_SYMBOL(rtc_lock); * nowtime is written into the registers of the CMOS clock, it will * jump to the next second precisely 500 ms later. Check the Motorola * MC146818A or Dallas DS12887 data sheet for details. - * - * BUG: This routine does not handle hour overflow properly; it just - * sets the minutes. Usually you'll only notice that after reboot! */ int mach_set_rtc_mmss(unsigned long nowtime) { - int real_seconds, real_minutes, cmos_minutes; - unsigned char save_control, save_freq_select; - unsigned long flags; + struct rtc_time tm; int retval = 0; - spin_lock_irqsave(&rtc_lock, flags); - - /* tell the clock it's being set */ - save_control = CMOS_READ(RTC_CONTROL); - CMOS_WRITE((save_control|RTC_SET), RTC_CONTROL); - - /* stop and reset prescaler */ - save_freq_select = CMOS_READ(RTC_FREQ_SELECT); - CMOS_WRITE((save_freq_select|RTC_DIV_RESET2), RTC_FREQ_SELECT); - - cmos_minutes = CMOS_READ(RTC_MINUTES); - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) - cmos_minutes = bcd2bin(cmos_minutes); - - /* - * since we're only adjusting minutes and seconds, - * don't interfere with hour overflow. This avoids - * messing with unknown time zones but requires your - * RTC not to be off by more than 15 minutes - */ - real_seconds = nowtime % 60; - real_minutes = nowtime / 60; - /* correct for half hour time zone */ - if (((abs(real_minutes - cmos_minutes) + 15)/30) & 1) - real_minutes += 30; - real_minutes %= 60; - - if (abs(real_minutes - cmos_minutes) < 30) { - if (!(save_control & RTC_DM_BINARY) || RTC_ALWAYS_BCD) { - real_seconds = bin2bcd(real_seconds); - real_minutes = bin2bcd(real_minutes); - } - CMOS_WRITE(real_seconds, RTC_SECONDS); - CMOS_WRITE(real_minutes, RTC_MINUTES); + rtc_time_to_tm(nowtime, &tm); + if (!rtc_valid_tm(&tm)) { + retval = set_rtc_time(&tm); + if (retval) + printk(KERN_ERR "%s: RTC write failed with error %d\n", + __FUNCTION__, retval); } else { - printk_once(KERN_NOTICE - "set_rtc_mmss: can't update from %d to %d\n", - cmos_minutes, real_minutes); - retval = -1; + printk(KERN_ERR + "%s: Invalid RTC value: write of %lx to RTC failed\n", + __FUNCTION__, nowtime); + retval = -EINVAL; } - - /* The following flags have to be released exactly in this order, - * otherwise the DS12887 (popular MC146818A clone with integrated - * battery and quartz) will not reset the oscillator and will not - * update precisely 500 ms later. You won't find this mentioned in - * the Dallas Semiconductor data sheets, but who believes data - * sheets anyway ... -- Markus Kuhn - */ - CMOS_WRITE(save_control, RTC_CONTROL); - CMOS_WRITE(save_freq_select, RTC_FREQ_SELECT); - - spin_unlock_irqrestore(&rtc_lock, flags); - return retval; } diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 90d8cc930f5..56f7fcfe7fa 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -82,7 +82,6 @@ #include <asm/timer.h> #include <asm/i8259.h> #include <asm/sections.h> -#include <asm/dmi.h> #include <asm/io_apic.h> #include <asm/ist.h> #include <asm/setup_arch.h> @@ -173,12 +172,10 @@ static struct resource bss_resource = { /* cpu data as detected by the assembly code in head.S */ struct cpuinfo_x86 new_cpu_data __cpuinitdata = { .wp_works_ok = -1, - .fdiv_bug = -1, }; /* common cpu data for all cpus */ struct cpuinfo_x86 boot_cpu_data __read_mostly = { .wp_works_ok = -1, - .fdiv_bug = -1, }; EXPORT_SYMBOL(boot_cpu_data); @@ -507,11 +504,14 @@ static void __init memblock_x86_reserve_range_setup_data(void) /* * Keep the crash kernel below this limit. On 32 bits earlier kernels * would limit the kernel to the low 512 MiB due to mapping restrictions. + * On 64bit, old kexec-tools need to under 896MiB. */ #ifdef CONFIG_X86_32 -# define CRASH_KERNEL_ADDR_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_LOW_MAX (512 << 20) +# define CRASH_KERNEL_ADDR_HIGH_MAX (512 << 20) #else -# define CRASH_KERNEL_ADDR_MAX MAXMEM +# define CRASH_KERNEL_ADDR_LOW_MAX (896UL<<20) +# define CRASH_KERNEL_ADDR_HIGH_MAX MAXMEM #endif static void __init reserve_crashkernel_low(void) @@ -521,19 +521,35 @@ static void __init reserve_crashkernel_low(void) unsigned long long low_base = 0, low_size = 0; unsigned long total_low_mem; unsigned long long base; + bool auto_set = false; int ret; total_low_mem = memblock_mem_size(1UL<<(32-PAGE_SHIFT)); + /* crashkernel=Y,low */ ret = parse_crashkernel_low(boot_command_line, total_low_mem, &low_size, &base); - if (ret != 0 || low_size <= 0) - return; + if (ret != 0) { + /* + * two parts from lib/swiotlb.c: + * swiotlb size: user specified with swiotlb= or default. + * swiotlb overflow buffer: now is hardcoded to 32k. + * We round it to 8M for other buffers that + * may need to stay low too. + */ + low_size = swiotlb_size_or_default() + (8UL<<20); + auto_set = true; + } else { + /* passed with crashkernel=0,low ? */ + if (!low_size) + return; + } low_base = memblock_find_in_range(low_size, (1ULL<<32), low_size, alignment); if (!low_base) { - pr_info("crashkernel low reservation failed - No suitable area found.\n"); + if (!auto_set) + pr_info("crashkernel low reservation failed - No suitable area found.\n"); return; } @@ -554,14 +570,22 @@ static void __init reserve_crashkernel(void) const unsigned long long alignment = 16<<20; /* 16M */ unsigned long long total_mem; unsigned long long crash_size, crash_base; + bool high = false; int ret; total_mem = memblock_phys_mem_size(); + /* crashkernel=XM */ ret = parse_crashkernel(boot_command_line, total_mem, &crash_size, &crash_base); - if (ret != 0 || crash_size <= 0) - return; + if (ret != 0 || crash_size <= 0) { + /* crashkernel=X,high */ + ret = parse_crashkernel_high(boot_command_line, total_mem, + &crash_size, &crash_base); + if (ret != 0 || crash_size <= 0) + return; + high = true; + } /* 0 means: find the address automatically */ if (crash_base <= 0) { @@ -569,7 +593,9 @@ static void __init reserve_crashkernel(void) * kexec want bzImage is below CRASH_KERNEL_ADDR_MAX */ crash_base = memblock_find_in_range(alignment, - CRASH_KERNEL_ADDR_MAX, crash_size, alignment); + high ? CRASH_KERNEL_ADDR_HIGH_MAX : + CRASH_KERNEL_ADDR_LOW_MAX, + crash_size, alignment); if (!crash_base) { pr_info("crashkernel reservation failed - No suitable area found.\n"); @@ -970,6 +996,7 @@ void __init setup_arch(char **cmdline_p) efi_init(); dmi_scan_machine(); + dmi_set_dump_stack_arch_desc(); /* * VMware detection requires dmi to be available, so this diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 9f190a2a00e..9c73b51817e 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -284,7 +284,7 @@ notrace static void __cpuinit start_secondary(void *unused) x86_cpuinit.setup_percpu_clockev(); wmb(); - cpu_idle(); + cpu_startup_entry(CPUHP_ONLINE); } void __init smp_store_boot_cpu_info(void) diff --git a/arch/x86/kernel/tls.c b/arch/x86/kernel/tls.c index 9d9d2f9e77a..f7fec09e3e3 100644 --- a/arch/x86/kernel/tls.c +++ b/arch/x86/kernel/tls.c @@ -3,13 +3,13 @@ #include <linux/sched.h> #include <linux/user.h> #include <linux/regset.h> +#include <linux/syscalls.h> #include <asm/uaccess.h> #include <asm/desc.h> #include <asm/ldt.h> #include <asm/processor.h> #include <asm/proto.h> -#include <asm/syscalls.h> #include "tls.h" @@ -89,11 +89,9 @@ int do_set_thread_area(struct task_struct *p, int idx, return 0; } -asmlinkage int sys_set_thread_area(struct user_desc __user *u_info) +SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, u_info) { - int ret = do_set_thread_area(current, -1, u_info, 1); - asmlinkage_protect(1, ret, u_info); - return ret; + return do_set_thread_area(current, -1, u_info, 1); } @@ -139,11 +137,9 @@ int do_get_thread_area(struct task_struct *p, int idx, return 0; } -asmlinkage int sys_get_thread_area(struct user_desc __user *u_info) +SYSCALL_DEFINE1(get_thread_area, struct user_desc __user *, u_info) { - int ret = do_get_thread_area(current, -1, u_info); - asmlinkage_protect(1, ret, u_info); - return ret; + return do_get_thread_area(current, -1, u_info); } int regset_tls_active(struct task_struct *target, diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c index 68bda7a8415..772e2a846de 100644 --- a/arch/x86/kernel/traps.c +++ b/arch/x86/kernel/traps.c @@ -12,6 +12,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/context_tracking.h> #include <linux/interrupt.h> #include <linux/kallsyms.h> #include <linux/spinlock.h> @@ -55,8 +56,7 @@ #include <asm/i387.h> #include <asm/fpu-internal.h> #include <asm/mce.h> -#include <asm/context_tracking.h> - +#include <asm/fixmap.h> #include <asm/mach_traps.h> #ifdef CONFIG_X86_64 @@ -176,34 +176,38 @@ do_trap(int trapnr, int signr, char *str, struct pt_regs *regs, #define DO_ERROR(trapnr, signr, str, name) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ - exception_enter(regs); \ + enum ctx_state prev_state; \ + \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, NULL); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } #define DO_ERROR_INFO(trapnr, signr, str, name, sicode, siaddr) \ dotraplinkage void do_##name(struct pt_regs *regs, long error_code) \ { \ siginfo_t info; \ + enum ctx_state prev_state; \ + \ info.si_signo = signr; \ info.si_errno = 0; \ info.si_code = sicode; \ info.si_addr = (void __user *)siaddr; \ - exception_enter(regs); \ + prev_state = exception_enter(); \ if (notify_die(DIE_TRAP, str, regs, error_code, \ trapnr, signr) == NOTIFY_STOP) { \ - exception_exit(regs); \ + exception_exit(prev_state); \ return; \ } \ conditional_sti(regs); \ do_trap(trapnr, signr, str, regs, error_code, &info); \ - exception_exit(regs); \ + exception_exit(prev_state); \ } DO_ERROR_INFO(X86_TRAP_DE, SIGFPE, "divide error", divide_error, FPE_INTDIV, @@ -226,14 +230,16 @@ DO_ERROR_INFO(X86_TRAP_AC, SIGBUS, "alignment check", alignment_check, /* Runs on IST stack */ dotraplinkage void do_stack_segment(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); if (notify_die(DIE_TRAP, "stack segment", regs, error_code, X86_TRAP_SS, SIGBUS) != NOTIFY_STOP) { preempt_conditional_sti(regs); do_trap(X86_TRAP_SS, SIGBUS, "stack segment", regs, error_code, NULL); preempt_conditional_cli(regs); } - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) @@ -241,7 +247,7 @@ dotraplinkage void do_double_fault(struct pt_regs *regs, long error_code) static const char str[] = "double fault"; struct task_struct *tsk = current; - exception_enter(regs); + exception_enter(); /* Return not checked because double check cannot be ignored */ notify_die(DIE_TRAP, str, regs, error_code, X86_TRAP_DF, SIGSEGV); @@ -261,8 +267,9 @@ dotraplinkage void __kprobes do_general_protection(struct pt_regs *regs, long error_code) { struct task_struct *tsk; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); conditional_sti(regs); #ifdef CONFIG_X86_32 @@ -300,12 +307,14 @@ do_general_protection(struct pt_regs *regs, long error_code) force_sig(SIGSEGV, tsk); exit: - exception_exit(regs); + exception_exit(prev_state); } /* May run on IST stack. */ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_code) { + enum ctx_state prev_state; + #ifdef CONFIG_DYNAMIC_FTRACE /* * ftrace must be first, everything else may cause a recursive crash. @@ -315,7 +324,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co ftrace_int3_handler(regs)) return; #endif - exception_enter(regs); + prev_state = exception_enter(); #ifdef CONFIG_KGDB_LOW_LEVEL_TRAP if (kgdb_ll_trap(DIE_INT3, "int3", regs, error_code, X86_TRAP_BP, SIGTRAP) == NOTIFY_STOP) @@ -336,7 +345,7 @@ dotraplinkage void __kprobes notrace do_int3(struct pt_regs *regs, long error_co preempt_conditional_cli(regs); debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_64 @@ -393,11 +402,12 @@ asmlinkage __kprobes struct pt_regs *sync_regs(struct pt_regs *eregs) dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) { struct task_struct *tsk = current; + enum ctx_state prev_state; int user_icebp = 0; unsigned long dr6; int si_code; - exception_enter(regs); + prev_state = exception_enter(); get_debugreg(dr6, 6); @@ -467,7 +477,7 @@ dotraplinkage void __kprobes do_debug(struct pt_regs *regs, long error_code) debug_stack_usage_dec(); exit: - exception_exit(regs); + exception_exit(prev_state); } /* @@ -561,17 +571,21 @@ void math_error(struct pt_regs *regs, int error_code, int trapnr) dotraplinkage void do_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_MF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void do_simd_coprocessor_error(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); math_error(regs, error_code, X86_TRAP_XF); - exception_exit(regs); + exception_exit(prev_state); } dotraplinkage void @@ -639,7 +653,9 @@ EXPORT_SYMBOL_GPL(math_state_restore); dotraplinkage void __kprobes do_device_not_available(struct pt_regs *regs, long error_code) { - exception_enter(regs); + enum ctx_state prev_state; + + prev_state = exception_enter(); BUG_ON(use_eager_fpu()); #ifdef CONFIG_MATH_EMULATION @@ -650,7 +666,7 @@ do_device_not_available(struct pt_regs *regs, long error_code) info.regs = regs; math_emulate(&info); - exception_exit(regs); + exception_exit(prev_state); return; } #endif @@ -658,15 +674,16 @@ do_device_not_available(struct pt_regs *regs, long error_code) #ifdef CONFIG_X86_32 conditional_sti(regs); #endif - exception_exit(regs); + exception_exit(prev_state); } #ifdef CONFIG_X86_32 dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) { siginfo_t info; + enum ctx_state prev_state; - exception_enter(regs); + prev_state = exception_enter(); local_irq_enable(); info.si_signo = SIGILL; @@ -678,7 +695,7 @@ dotraplinkage void do_iret_error(struct pt_regs *regs, long error_code) do_trap(X86_TRAP_IRET, SIGILL, "iret exception", regs, error_code, &info); } - exception_exit(regs); + exception_exit(prev_state); } #endif @@ -753,6 +770,14 @@ void __init trap_init(void) #endif /* + * Set the IDT descriptor to a fixed read-only location, so that the + * "sidt" instruction will not leak the location of the kernel, and + * to defend the IDT against arbitrary memory write vulnerabilities. + * It will be reloaded in cpu_init() */ + __set_fixmap(FIX_RO_IDT, __pa_symbol(idt_table), PAGE_KERNEL_RO); + idt_descr.address = fix_to_virt(FIX_RO_IDT); + + /* * Should be a barrier for any external CPU state: */ cpu_init(); diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c index 4b9ea101fe3..098b3cfda72 100644 --- a/arch/x86/kernel/tsc.c +++ b/arch/x86/kernel/tsc.c @@ -768,7 +768,8 @@ static cycle_t read_tsc(struct clocksource *cs) static void resume_tsc(struct clocksource *cs) { - clocksource_tsc.cycle_last = 0; + if (!boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) + clocksource_tsc.cycle_last = 0; } static struct clocksource clocksource_tsc = { @@ -939,6 +940,9 @@ static int __init init_tsc_clocksource(void) clocksource_tsc.flags &= ~CLOCK_SOURCE_IS_CONTINUOUS; } + if (boot_cpu_has(X86_FEATURE_NONSTOP_TSC_S3)) + clocksource_tsc.flags |= CLOCK_SOURCE_SUSPEND_NONSTOP; + /* * Trust the results of the earlier calibration on systems * exporting a reliable TSC. diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 0ba4cfb4f41..2ed845928b5 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -697,3 +697,32 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) send_sig(SIGTRAP, current, 0); return ret; } + +unsigned long +arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) +{ + int rasize, ncopied; + unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ + + rasize = is_ia32_task() ? 4 : 8; + ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize); + if (unlikely(ncopied)) + return -1; + + /* check whether address has been already hijacked */ + if (orig_ret_vaddr == trampoline_vaddr) + return orig_ret_vaddr; + + ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); + if (likely(!ncopied)) + return orig_ret_vaddr; + + if (ncopied != rasize) { + pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " + "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); + + force_sig_info(SIGSEGV, SEND_SIG_FORCED, current); + } + + return -1; +} diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index 22a1530146a..10c4f3006af 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -94,10 +94,6 @@ SECTIONS _text = .; /* bootstrapping code */ HEAD_TEXT -#ifdef CONFIG_X86_32 - . = ALIGN(PAGE_SIZE); - *(.text..page_aligned) -#endif . = ALIGN(8); _stext = .; TEXT_TEXT |